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

    Neuronpedia

    INDEX
    Explanations

    document

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .with
    -0.07
    -buttons
    -0.07
    _prev
    -0.07
    with
    -0.06
     criticize
    -0.06
     chairs
    -0.06
    (next
    -0.06
    (CH
    -0.06
    .nextToken
    -0.06
     seen
    -0.06
    POSITIVE LOGITS
    197
    0.07
     файла
    0.07
    \Array
    0.07
    QB
    0.07
    exceptions
    0.06
    ської
    0.06
     замов
    0.06
    .OR
    0.06
    وسف
    0.06
     galaxies
    0.06
    Act Density 0.004%

    No Known Activations