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

    Neuronpedia

    INDEX
    Explanations

    terms related to mathematical concepts and formal expressions

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

    section indicators and citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    InstrumentedTest
    -0.69
     surla
    -0.64
     kaynağından
    -0.62
    Tembelea
    -0.57
     ModelExpression
    -0.57
    ConstraintMaker
    -0.54
    הערות
    -0.53
     ligiloj
    -0.53
    請繼續往下閱讀
    -0.53
    Erstellt
    -0.52
    POSITIVE LOGITS
    Corollary
    0.40
     emerging
    0.40
     emergent
    0.39
     jade
    0.37
    FOLIO
    0.37
     Everett
    0.36
     gamin
    0.36
    おか
    0.36
    emer
    0.35
    erah
    0.34
    Act Density 0.008%

    No Known Activations