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

    Neuronpedia

    INDEX
    Explanations

    AP

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    atr
    -0.07
    anki
    -0.06
    _connect
    -0.06
     philosophy
    -0.06
     Thường
    -0.06
    èn
    -0.06
     tourism
    -0.06
    kar
    -0.06
     Solar
    -0.06
     programmes
    -0.06
    POSITIVE LOGITS
     Barnett
    0.07
     governing
    0.06
    194
    0.06
    __,↵
    0.06
    صب
    0.06
    原本
    0.06
     Discounts
    0.06
     Bucket
    0.06
     دختر
    0.06
    onestly
    0.06
    Act Density 0.003%

    No Known Activations