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

    Neuronpedia

    INDEX
    Explanations

    Foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <Message
    -0.07
    _digits
    -0.07
    zet
    -0.07
    uka
    -0.07
     response
    -0.06
     Ratio
    -0.06
     Guinness
    -0.06
     Invoice
    -0.06
    Mensaje
    -0.06
     surprise
    -0.06
    POSITIVE LOGITS
     грун
    0.07
    इसक
    0.06
    .PictureBoxSizeMode
    0.06
     بغ
    0.06
     metam
    0.06
     incarn
    0.06
    ModelError
    0.06
     paranormal
    0.06
     democrat
    0.06
    rops
    0.06
    Act Density 0.002%

    No Known Activations