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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate recalling, understanding, or conveying information

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

    as far as I can tell

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    pushFollow
    -0.52
     ویکی‌پدی
    -0.44
     مرئيه
    -0.43
    锈钢
    -0.41
     tortuga
    -0.41
     Walkover
    -0.40
     Signalez
    -0.40
    intellij
    -0.38
    PMailer
    -0.38
    featureID
    -0.37
    POSITIVE LOGITS
     zufolge
    0.47
    enumi
    0.47
    Diweddarwch
    0.45
     bedankt
    0.45
    GraphicsUnit
    0.43
    altezza
    0.41
    ondheim
    0.40
     guère
    0.40
    Спољашње
    0.40
    XmlAccessType
    0.40
    Act Density 0.052%

    No Known Activations