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

    Neuronpedia

    INDEX
    Explanations

    interrogative and introductory words that initiate questions or inquiries

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

    Questions starting with "How", "Can", or "Im"

    np_acts-logits-general · gemini-2.0-flash

    questions and introductory phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GTCX
    -0.78
     CURIAM
    -0.68
    المناصب
    -0.67
    +:+
    -0.66
     تضيفلها
    -0.65
    InitVars
    -0.65
    下载附件
    -0.64
     للمعارف
    -0.63
     MainAxisSize
    -0.62
     ModelExpression
    -0.61
    POSITIVE LOGITS
    Incomplete
    0.41
    很有
    0.35
     Verf
    0.32
    Kindly
    0.31
     images
    0.30
     бази
    0.30
    SerialNumber
    0.30
     documents
    0.30
     update
    0.30
     incomplete
    0.30
    Act Density 0.013%

    No Known Activations