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

    Neuronpedia

    INDEX
    Explanations

    statistics, tables

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    WWW
    -0.07
     productive
    -0.07
    .med
    -0.06
     Beng
    -0.06
     Kur
    -0.06
    _Name
    -0.06
    _infos
    -0.06
    lash
    -0.06
     whip
    -0.06
     thải
    -0.06
    POSITIVE LOGITS
     खतर
    0.07
    .assertNot
    0.07
     Definitely
    0.06
    _FORCE
    0.06
     problém
    0.06
     weaknesses
    0.06
    _RESERVED
    0.06
     FFT
    0.06
    -writing
    0.06
    dz
    0.06
    Act Density 0.001%

    No Known Activations