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

    Neuronpedia

    INDEX
    Explanations

    expressions of boredom or frustration

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

    I cannot help myself

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tartalomajánló
    -0.80
    艋
    -0.71
    دانشنامهٔ
    -0.63
    +#+#
    -0.62
     Roskov
    -0.60
    TagMode
    -0.59
    setVerticalGroup
    -0.59
     queſta
    -0.59
     كومونز
    -0.58
    ロウィン
    -0.56
    POSITIVE LOGITS
     psicológica
    0.36
     amarilla
    0.33
    printStats
    0.32
     literario
    0.32
     pintado
    0.31
     Antwort
    0.31
     humanidad
    0.30
     humanidade
    0.30
     físicos
    0.29
     zaś
    0.29
    Act Density 0.012%

    No Known Activations