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

    Neuronpedia

    INDEX
    Explanations

    expressions conveying personal identity and self-reflection

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

    possessive pronouns followed by nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    httphttps
    -0.55
    exitRule
    -0.49
    -0.48
    addCriterion
    -0.48
     للاسماء
    -0.47
    CodeAttribute
    -0.46
    epresidente
    -0.46
    CloseOperation
    -0.45
    providedIn
    -0.44
    writeFieldEnd
    -0.44
    POSITIVE LOGITS
     inner
    1.30
     Inner
    1.10
    inner
    1.07
    Inner
    1.05
     INNER
    0.93
    INNER
    0.82
     innere
    0.77
     inneren
    0.76
    內
    0.69
     innermost
    0.68
    Act Density 0.045%

    No Known Activations