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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    This neuron fires on documentation comment keywords (like “Return,” “Get,” “Defines,” etc.) in code comments.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     porn
    -0.06
    _QUOTES
    -0.06
    (Member
    -0.06
     maneu
    -0.06
    _delete
    -0.06
     Gef
    -0.06
    ouchers
    -0.06
    Illustr
    -0.05
    .MiddleCenter
    -0.05
     hott
    -0.05
    POSITIVE LOGITS
     ij
    0.07
     strengthen
    0.07
     tid
    0.07
    high
    0.06
    krét
    0.06
    anity
    0.06
    ้าก
    0.06
    ura
    0.06
     insanely
    0.06
    xfb
    0.06
    Act Density 0.006%

    No Known Activations