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

    Neuronpedia

    INDEX
    Explanations

    Identifiers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Aud
    -0.07
    Disney
    -0.07
    discord
    -0.07
    .radioButton
    -0.07
     thrift
    -0.07
     вок
    -0.07
     определ
    -0.07
     Transport
    -0.06
     Seeds
    -0.06
     incentive
    -0.06
    POSITIVE LOGITS
    csrf
    0.06
     CAS
    0.06
    ezi
    0.06
    FG
    0.06
    Configure
    0.06
    扫
    0.06
    奴
    0.06
    TEMP
    0.06
    滿
    0.06
     onPostExecute
    0.05
    Act Density 0.062%

    No Known Activations