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

    Neuronpedia

    INDEX
    Explanations

    references to central subjects or pronouns in discussions

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

    text following common words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     onBind
    -0.43
    Disliked
    -0.35
     pleaſure
    -0.35
     nonUne
    -0.34
     fiber
    -0.34
    TypedDataSet
    -0.34
     traveler
    -0.33
    ])),
    -0.33
    ))),
    -0.32
    ſelves
    -0.32
    POSITIVE LOGITS
     للمعارف
    0.79
    出版年
    0.61
    MENAFN
    0.54
    تقاوى
    0.52
    Rujukan
    0.52
    mær
    0.50
     specchio
    0.50
    muerzo
    0.48
    безпе
    0.48
    MessageOf
    0.47
    Act Density 0.060%

    No Known Activations