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

    Neuronpedia

    INDEX
    Explanations

    references to citation formats or numbered lists

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

    scientific paper citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     proporción
    -0.53
    @[+][
    -0.50
     propOrder
    -0.48
    Bibliograf
    -0.47
     Utilizamos
    -0.45
     CreateTagHelper
    -0.43
     probabilidad
    -0.41
     colgante
    -0.41
    inSlope
    -0.40
     parís
    -0.40
    POSITIVE LOGITS
    0
    0.74
    PageContext
    0.55
    AutoScaleMode
    0.54
     ۰
    0.50
    期刊论文
    0.48
    Koh
    0.47
     صفر
    0.46
     Eternity
    0.46
    JAMIN
    0.46
    Etern
    0.45
    Act Density 0.005%

    No Known Activations