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

    Neuronpedia

    INDEX
    Explanations

    mathematical coefficients

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric tokens (including integers, decimal values, and fractional expressions).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    bone
    -0.07
    udios
    -0.06
    .GetUser
    -0.06
     ****************************************************************
    -0.06
    acid
    -0.06
    .di
    -0.06
     Erik
    -0.06
    ila
    -0.06
    .classList
    -0.06
    oid
    -0.06
    POSITIVE LOGITS
    род
    0.08
     nå
    0.07
     سلامت
    0.07
    اید
    0.07
     استان
    0.07
     enforcing
    0.07
     fearing
    0.07
     droits
    0.07
     llegar
    0.06
     celé
    0.06
    Act Density 0.009%

    No Known Activations