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

    Neuronpedia

    INDEX
    Explanations

    say "programming related" words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ivr
    -0.07
     ZIP
    -0.07
    wer
    -0.07
    abler
    -0.07
    pike
    -0.07
     материал
    -0.07
    .Buffer
    -0.06
    орая
    -0.06
    Cast
    -0.06
    lein
    -0.06
    POSITIVE LOGITS
    _install
    0.07
     realtime
    0.07
    FI
    0.07
     تن
    0.06
    agi
    0.06
     Adult
    0.06
     लगत
    0.06
    _TP
    0.06
     tasty
    0.06
     склад
    0.06
    Act Density 0.054%

    No Known Activations