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

    Neuronpedia

    INDEX
    Explanations

    hyphen

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (pow
    -0.07
    Enabled
    -0.07
    Selected
    -0.07
    Column
    -0.07
    _enabled
    -0.07
    -assisted
    -0.07
     dazzling
    -0.07
     pow
    -0.07
     Variety
    -0.07
    ایه
    -0.07
    POSITIVE LOGITS
     disadvantages
    0.09
    iril
    0.08
    opedic
    0.08
    ações
    0.08
    aciji
    0.08
     располага
    0.08
    tral
    0.08
    ’intérieur
    0.08
    ્પાદ
    0.08
     ntụ
    0.08
    Act Density 0.055%

    No Known Activations