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

    Neuronpedia

    INDEX
    Explanations

    syntax elements and formatting indicators in code or markup languages

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

    variant significance and modifier

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     médicale
    -0.59
     étoit
    -0.49
     mourut
    -0.45
     alberi
    -0.43
     murale
    -0.43
     chrétienne
    -0.43
     enfans
    -0.42
     Juifs
    -0.42
     Defensa
    -0.42
     tehd
    -0.40
    POSITIVE LOGITS
     variant
    1.13
     Variant
    0.97
     variants
    0.96
     Variants
    0.93
    variant
    0.91
     variation
    0.89
    Variant
    0.89
    VARIANT
    0.88
    variants
    0.86
    Variants
    0.84
    Act Density 0.022%

    No Known Activations