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

    Neuronpedia

    INDEX
    Explanations

    specific identifiers and formatted characters

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

    Code, symbols, and uncommon formatting

    np_acts-logits-general · gemini-2.0-flash

    .debug records

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    المشاركات
    -0.48
     CURIAM
    -0.47
    الحياه
    -0.47
     ddelweddau
    -0.43
    ISupport
    -0.42
    Kjelder
    -0.42
    Véxase
    -0.41
    InjectAttribute
    -0.40
     استنادى
    -0.40
    ValueStyle
    -0.40
    POSITIVE LOGITS
    parsedMessage
    0.48
     насељу
    0.46
    StoryboardSegue
    0.46
    RTEX
    0.43
     beider
    0.41
     disegni
    0.41
    UrlResolution
    0.40
    unknownFields
    0.40
    smithy
    0.39
    apimachinery
    0.38
    Act Density 0.599%

    No Known Activations