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

    Neuronpedia

    INDEX
    Explanations

    Numerical data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ategorias
    -0.07
    _percentage
    -0.07
     defendant
    -0.07
     adviser
    -0.06
     проблемы
    -0.06
     статті
    -0.06
    럽
    -0.06
    304
    -0.06
     motivational
    -0.06
     skutečnosti
    -0.06
    POSITIVE LOGITS
    (fields
    0.07
     Pair
    0.07
     -----
    0.06
    .set
    0.06
     respective
    0.06
     Adjust
    0.06
    _FUN
    0.06
    CLUDE
    0.06
     getClass
    0.06
    ьте
    0.06
    Act Density 0.233%

    No Known Activations