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

    Neuronpedia

    INDEX
    Explanations

    references to literary works and significant titles

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

    titles or proper nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Билгалдахарш
    -0.61
    UnsafeEnabled
    -0.56
    ंदीखरीदारी
    -0.56
    tagHelperRunner
    -0.56
    makeText
    -0.52
    chyma
    -0.49
     ModelExpression
    -0.49
     ब्रेकडाउन
    -0.48
     Signalez
    -0.47
    KURZBESCHREIBUNG
    -0.47
    POSITIVE LOGITS
     للاسماء
    0.49
    owań
    0.36
    XmlEnum
    0.34
     Matrices
    0.33
    jąc
    0.33
     auprès
    0.32
     Inquiry
    0.32
    0.32
    thenReturn
    0.32
     zakład
    0.31
    Act Density 0.065%

    No Known Activations