Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    weather

    np_max-act · gemini-2.0-flash

    discussions surrounding climate change and its anthropogenic impacts.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron consistently activates on terms naming climate‐change evidence metrics and impacts (e.g. “temperature records,” “sea-level rise,” “shrinking ice sheets,” “extreme weather events”), i.e. phrases describing measurable signs or consequences of climate change.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Parks
    -0.06
    腾
    -0.06
     percept
    -0.06
     Pride
    -0.06
    离
    -0.06
    tgt
    -0.06
     usable
    -0.06
    _validator
    -0.06
    acket
    -0.06
    까요
    -0.06
    POSITIVE LOGITS
    .Stack
    0.07
    :UI
    0.07
    řila
    0.07
    ствен
    0.06
    (CC
    0.06
     الى
    0.06
     arbitr
    0.06
    licative
    0.06
     rost
    0.06
    _REL
    0.06
    Act Density 0.009%

    No Known Activations