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

    Neuronpedia

    INDEX
    Explanations

    {

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Resolution
    -0.07
    lications
    -0.07
    .Time
    -0.07
    .IsNotNull
    -0.07
    contro
    -0.07
     cont
    -0.06
    _classifier
    -0.06
     frustration
    -0.06
    访
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     dokładnie
    0.07
    روب
    0.07
     cryptocurrencies
    0.07
     certifications
    0.07
    离开
    0.06
     consciousness
    0.06
    ق
    0.06
    气体
    0.06
     Gerald
    0.06
    otas
    0.06
    Act Density 0.014%

    No Known Activations