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

    Neuronpedia

    INDEX
    Explanations

    gut

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    FindBy
    -0.07
    Card
    -0.06
    ského
    -0.06
     Hindi
    -0.06
    (V
    -0.06
    _confirmation
    -0.06
     Asi
    -0.06
     nearer
    -0.06
     이전
    -0.06
    (context
    -0.06
    POSITIVE LOGITS
    ар
    0.07
    �
    0.07
    тора
    0.07
    oleon
    0.07
    attered
    0.07
    Mongo
    0.07
    тии
    0.07
    管
    0.06
    /App
    0.06
    wid
    0.06
    Act Density 0.002%

    No Known Activations