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

    Neuronpedia

    INDEX
    Explanations

    base

    np_max-act · gemini-2.0-flash

    numerical conversions related to base systems.

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

    The neuron fires on mentions of numeric bases (i.e. references to “base” and the following base identifiers in base‐conversion prompts).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    織
    -0.07
    bread
    -0.07
     ern
    -0.07
    Please
    -0.06
    _income
    -0.06
     albums
    -0.06
    Enabled
    -0.06
     exploration
    -0.06
    che
    -0.06
    SCAN
    -0.06
    POSITIVE LOGITS
    ücü
    0.06
     vets
    0.06
    <cv
    0.06
    iplinary
    0.06
     classNames
    0.06
    .open
    0.06
    bang
    0.06
    ，加
    0.06
     sahibi
    0.06
    abbix
    0.05
    Act Density 0.001%

    No Known Activations