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

    Neuronpedia

    INDEX
    Explanations

    Uncertainty or questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -than
    -0.07
     avoids
    -0.07
     excursion
    -0.06
    市
    -0.06
    Hostname
    -0.06
     MESSAGE
    -0.06
     दल
    -0.06
    alpha
    -0.06
    clave
    -0.06
    optim
    -0.06
    POSITIVE LOGITS
    balls
    0.07
     rapper
    0.06
    .DefaultCellStyle
    0.06
    .Perform
    0.06
    _asc
    0.06
     arise
    0.06
    を行
    0.06
    utches
    0.06
     McGr
    0.06
    lettes
    0.06
    Act Density 0.023%

    No Known Activations