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

    Neuronpedia

    INDEX
    Explanations

    parentheses and hashtags

    np_max-act · gemini-2.0-flash

    The neuron fires on code‐style method or function identifiers (e.g. names followed by “(” in calls, generic type parameters in angle brackets, or “#anchor” fragments in documentation URLs).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    technical terms and references related to coding and documentation.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Lv
    -0.06
     anonymity
    -0.06
     نموده
    -0.06
     Hãy
    -0.06
    沈
    -0.06
     갖
    -0.06
     malformed
    -0.06
     Era
    -0.06
     Parish
    -0.06
    _paint
    -0.05
    POSITIVE LOGITS
     khả
    0.07
     codes
    0.07
     nổi
    0.07
    )::
    0.06
     mediaPlayer
    0.06
     Krishna
    0.06
    IOR
    0.06
    name
    0.06
    860
    0.06
    .SetFloat
    0.06
    Act Density 0.024%

    No Known Activations