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

    Neuronpedia

    INDEX
    Explanations

    references to censorship or controversial expressions

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

    preceding concepts of insignificance or possibility

    np_acts-logits-general · gemini-2.0-flash

    mere presence or slightest sign

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SourceChecksum
    -0.83
    migrationBuilder
    -0.83
    OGND
    -0.72
     utafitiHapana
    -0.70
    ("]");
    -0.69
     nahilalakip
    -0.67
    istoitu
    -0.67
    følgelig
    -0.67
    parsedMessage
    -0.66
    findpost
    -0.66
    POSITIVE LOGITS
     slightest
    1.32
     touch
    1.17
     touched
    1.13
     mention
    1.05
     moindre
    0.97
     anything
    0.92
     touches
    0.91
     sight
    0.91
     any
    0.91
     mentioning
    0.90
    Act Density 0.340%

    No Known Activations