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

    Neuronpedia

    INDEX
    Explanations

    's

    np_max-act · gemini-2.0-flash

    discussions surrounding health policy and societal issues.

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

    The neuron responds to hedging or qualifying discourse markers that soften or qualify statements.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    epoch
    -0.07
     змі
    -0.06
    /sec
    -0.06
    delegate
    -0.06
    ibia
    -0.06
     famously
    -0.06
    ncmp
    -0.06
     convex
    -0.06
     شي
    -0.06
     گذاری
    -0.06
    POSITIVE LOGITS
    <bits
    0.07
     Richards
    0.07
     مارس
    0.07
    ICAL
    0.06
    untime
    0.06
    0.06
     ]);
    0.06
    _FLUSH
    0.06
    ियर
    0.06
    Friends
    0.06
    Act Density 0.044%

    No Known Activations