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

    Neuronpedia

    INDEX
    Explanations

    evidence or claims that require validation or demonstration

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

    demonstrate that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    reportWebVitals
    -0.83
     صوتيه
    -0.73
     EconPapers
    -0.70
     ModelExpression
    -0.68
    parsedMessage
    -0.66
    tagHelperRunner
    -0.66
     ProtoMessage
    -0.64
    styleType
    -0.63
    richTextPanel
    -0.63
    GraphicsUnit
    -0.62
    POSITIVE LOGITS
     proving
    0.74
     demostrado
    0.72
     proof
    0.71
     demonstration
    0.70
     prove
    0.70
     demonstrated
    0.70
     demostr
    0.70
    nachweis
    0.69
     proven
    0.69
     demonstrating
    0.68
    Act Density 0.308%

    No Known Activations