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

    Neuronpedia

    INDEX
    Explanations

    references to excessive amounts or excessiveness in various contexts

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

    excess of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     almohada
    -0.44
     Inscrivez
    -0.44
     chaqueta
    -0.44
     Democrá
    -0.43
     extranjera
    -0.43
     Jurí
    -0.42
     Wikiseite
    -0.41
    umumkan
    -0.41
     AssemblyCulture
    -0.40
     plateado
    -0.40
    POSITIVE LOGITS
     Excess
    0.84
     excess
    0.83
     exceeds
    0.77
     exceeding
    0.77
    Excess
    0.75
     exceeded
    0.74
     exceed
    0.71
    excess
    0.69
    выше
    0.58
     excesses
    0.57
    Act Density 0.004%

    No Known Activations