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

    Neuronpedia

    INDEX
    Explanations

    repeated punctuation marks or symbols within code snippets

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

    models, Game, Weather, motion, Zone

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     resourceCulture
    -0.71
    tagHelperRunner
    -0.61
    parsedMessage
    -0.59
    enderror
    -0.58
    TypedDataSet
    -0.54
    addCriterion
    -0.54
     ModelExpression
    -0.53
    FunctionFlags
    -0.53
     HasFactory
    -0.53
    存于互联网档案馆
    -0.48
    POSITIVE LOGITS
    ⤹
    0.46
    Portale
    0.41
    })$}
    0.39
    ➌
    0.39
     Salas
    0.39
     Speicher
    0.39
     Mengen
    0.39
     Murders
    0.38
    haben
    0.38
     censi
    0.38
    Act Density 0.002%

    No Known Activations