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

    Neuronpedia

    INDEX
    Explanations

    references to error handling and success messages

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

    info, song, vote, month

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     upon
    -0.30
    </em>
    -0.28
    égard
    -0.28
     int
    -0.28
    SequentialGroup
    -0.28
     strict
    -0.28
     whether
    -0.27
     DA
    -0.27
     ten
    -0.27
    complexContent
    -0.27
    POSITIVE LOGITS
    parsedMessage
    0.97
    хьтан
    0.73
     يتيمه
    0.69
    expandindo
    0.68
     <=",
    0.64
    contentLoaded
    0.62
    InputBorder
    0.62
    GEBURTSDATUM
    0.61
    StructEnd
    0.60
     ModelExpression
    0.59
    Act Density 0.040%

    No Known Activations