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

    Neuronpedia

    INDEX
    Explanations

    Bul

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric tokens and measurements (e.g. digits, decimal values, counts).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Nad
    -0.07
     Пост
    -0.07
     FH
    -0.07
    acons
    -0.06
    orf
    -0.06
    Haz
    -0.06
     Src
    -0.06
     WAR
    -0.06
     Ferrari
    -0.06
    goo
    -0.06
    POSITIVE LOGITS
    (keyword
    0.07
     بشكل
    0.06
    커스
    0.06
     reasoned
    0.06
     βρί
    0.06
    lie
    0.06
    บาล
    0.06
     ilaç
    0.06
     deve
    0.06
    _generic
    0.06
    Act Density 0.000%

    No Known Activations