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

    Neuronpedia

    INDEX
    Explanations

    documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Radio
    -0.06
     Week
    -0.06
     prendre
    -0.06
     Rum
    -0.06
     offset
    -0.06
     Cats
    -0.06
     imageUrl
    -0.06
    στά
    -0.06
     Maher
    -0.06
     Stop
    -0.06
    POSITIVE LOGITS
    duğ
    0.07
     vestib
    0.07
     досить
    0.07
     втор
    0.07
    heets
    0.07
    acie
    0.06
    аниц
    0.06
     aff
    0.06
    활동
    0.06
    _derivative
    0.06
    Act Density 0.093%

    No Known Activations