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

    Neuronpedia

    INDEX
    Explanations

    code-related syntax and function definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code containing parentheses and boolean values

    np_acts-logits-general · gemini-2.0-flash

    follows that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     lanjut
    -0.46
    </em>
    -0.46
     Winfrey
    -0.45
    这家伙
    -0.43
    Biografi
    -0.42
    ала
    -0.40
     mortos
    -0.40
    da
    -0.40
    Deskripsi
    -0.39
     épaules
    -0.39
    POSITIVE LOGITS
    ArgsConstructor
    0.89
     autorytatywna
    0.86
    reportWebVitals
    0.82
     تضيفلها
    0.77
    addCriterion
    0.77
     $_[
    0.73
     Administrativna
    0.70
     שוליים
    0.69
    ACIAS
    0.66
    Билгалдахарш
    0.66
    Act Density 0.147%

    No Known Activations