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

    Neuronpedia

    INDEX
    Explanations

    expressions of surprise or unexpectedness

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

    surprise, sigh, among

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    seguida
    -0.41
    Vri
    -0.36
     Sociales
    -0.36
     nonUne
    -0.36
     inmediato
    -0.35
    transQ
    -0.35
    httphttps
    -0.34
     verrou
    -0.34
    Spéc
    -0.33
     basée
    -0.33
    POSITIVE LOGITS
     ModelExpression
    0.66
     '\\;'
    0.63
    EndContext
    0.63
    underbrace
    0.59
    TargetException
    0.52
    __(/*!
    0.52
    bootstrapcdn
    0.50
    FunctionFlags
    0.49
    PropertyChanging
    0.49
    ModelSerializer
    0.48
    Act Density 0.282%

    No Known Activations