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

    Neuronpedia

    INDEX
    Explanations

    level

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ht
    -0.07
    setName
    -0.07
    _TX
    -0.06
     abroad
    -0.06
    _lot
    -0.06
     duro
    -0.06
     computational
    -0.06
     strtolower
    -0.06
     Parameter
    -0.06
    PushButton
    -0.06
    POSITIVE LOGITS
    .counter
    0.06
    appoint
    0.06
    Formula
    0.06
    Κα
    0.06
    소개
    0.06
     Furniture
    0.06
     khẳng
    0.06
     βο
    0.06
    _cre
    0.06
    esting
    0.06
    Act Density 0.009%

    No Known Activations