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

    Neuronpedia

    INDEX
    Explanations

    first

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    dv
    -0.07
     ste
    -0.07
    เฟ
    -0.06
    _padding
    -0.06
    parity
    -0.06
     dried
    -0.06
    .Lo
    -0.06
     spanking
    -0.06
     Undo
    -0.06
     pwd
    -0.06
    POSITIVE LOGITS
    ेख
    0.07
     conceive
    0.07
    跨
    0.06
     chronological
    0.06
     momentos
    0.06
     olmadığı
    0.06
    _elems
    0.06
    madığı
    0.06
     momento
    0.06
    ESSAGES
    0.06
    Act Density 0.026%

    No Known Activations