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

    Neuronpedia

    INDEX
    Explanations

    read

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cof
    -0.07
    _TER
    -0.06
     Deg
    -0.06
     theolog
    -0.06
    athlon
    -0.06
    _ter
    -0.06
     bedding
    -0.06
    GAN
    -0.06
    파
    -0.06
    셀
    -0.06
    POSITIVE LOGITS
    рич
    0.07
    .sav
    0.07
    .SelectCommand
    0.06
    Configuration
    0.06
    ória
    0.06
    にある
    0.06
     either
    0.06
    crets
    0.06
     Vik
    0.06
    ुख
    0.06
    Act Density 0.007%

    No Known Activations