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

    Neuronpedia

    INDEX
    Explanations

    time periods

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Rosen
    -0.08
     Unters
    -0.07
     Под
    -0.07
     fout
    -0.07
     Billy
    -0.07
     confronting
    -0.06
    ぇ
    -0.06
     Prefix
    -0.06
    Telefono
    -0.06
    datal
    -0.06
    POSITIVE LOGITS
    .getElementsBy
    0.06
     provincia
    0.06
    Disclosure
    0.06
    _moves
    0.06
     joys
    0.06
     перш
    0.06
    .addField
    0.06
    0.06
    rouw
    0.06
     handsome
    0.06
    Act Density 0.010%

    No Known Activations