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

    Neuronpedia

    INDEX
    Explanations

    .com

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Express
    -0.07
     ripe
    -0.07
     forget
    -0.06
    Easy
    -0.06
    .measure
    -0.06
    ouched
    -0.06
    anti
    -0.06
     Aux
    -0.06
    fen
    -0.06
     abundant
    -0.06
    POSITIVE LOGITS
     kd
    0.07
     전국
    0.07
    mě
    0.07
    (delegate
    0.06
    (Route
    0.06
    足球
    0.06
     Hệ
    0.06
     retorna
    0.06
    .learn
    0.06
     言
    0.06
    Act Density 0.000%

    No Known Activations