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

    Neuronpedia

    INDEX
    Explanations

    references to original or initial ideas, reports, or complaints

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

    original/initial + noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    InjectAttribute
    -0.53
    Portail
    -0.49
    ControllerAdvice
    -0.46
     रेटिंग
    -0.44
     jScrollPane
    -0.43
    حياته
    -0.43
    WireFormat
    -0.43
    GEBURTS
    -0.43
    تقاوى
    -0.40
     للاسماء
    -0.40
    POSITIVE LOGITS
     originally
    0.88
     original
    0.85
     ursprünglichen
    0.84
     ursprüng
    0.84
    original
    0.81
    Original
    0.81
     originais
    0.79
     ORIGINAL
    0.79
     eredeti
    0.78
     initially
    0.77
    Act Density 0.030%

    No Known Activations