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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric tokens—especially decimal numbers—highlighting floating-point values in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    огою
    -0.07
    _verification
    -0.07
    ']}}</
    -0.07
     สถาน
    -0.07
     backgrounds
    -0.06
    latitude
    -0.06
    178
    -0.06
    (channel
    -0.06
     Juventus
    -0.06
    131
    -0.06
    POSITIVE LOGITS
    Ac
    0.06
    Rent
    0.06
    _requests
    0.06
    ۳۰
    0.06
    asjon
    0.06
    гор
    0.06
    ―
    0.06
     حق
    0.06
     depos
    0.06
     advised
    0.06
    Act Density 0.011%

    No Known Activations