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

    Neuronpedia

    INDEX
    Explanations

    expressions of uncertainty or lack of expertise

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

    conjunctions and negations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     observ
    -0.35
    RenderAtEndOf
    -0.34
    atrix
    -0.34
    detectChanges
    -0.34
    InsertCommand
    -0.33
    ptest
    -0.33
    Collegamenti
    -0.32
    🦵
    -0.31
    (":");
    -0.30
     impea
    -0.30
    POSITIVE LOGITS
     EconPapers
    0.57
     للاسماء
    0.54
    abetes
    0.53
     informée
    0.52
    ఔ
    0.50
     Biôgrafia
    0.48
    parsedMessage
    0.47
     Taktlose
    0.46
    脚注の使い方
    0.46
     تخصص
    0.45
    Act Density 0.036%

    No Known Activations