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

    Neuronpedia

    INDEX
    Explanations

    actions related to combat and grappling techniques

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

    proper nouns and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Crest
    -0.42
     isabel
    -0.41
    Eras
    -0.41
    Linden
    -0.40
     ſtand
    -0.40
     AssemblyCompany
    -0.40
    FAM
    -0.40
     Moderna
    -0.40
     quæ
    -0.39
     Institute
    -0.39
    POSITIVE LOGITS
    SourceChecksum
    0.62
    expandindo
    0.58
     ویکی‌پدی
    0.57
    WebElementEntity
    0.56
    parsedMessage
    0.56
     agresión
    0.55
     BoxFit
    0.55
     choked
    0.50
    readAs
    0.50
    UnusedPrivate
    0.50
    Act Density 0.050%

    No Known Activations