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

    Neuronpedia

    INDEX
    Explanations

    mentions of guides or helpful resources

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

    recap retrospective hindsight

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tagHelperRunner
    -0.72
    Diweddarwch
    -0.61
    inSlope
    -0.59
    뀔
    -0.55
    Autoritní
    -0.50
    MigrationBuilder
    -0.49
    ğraf
    -0.48
    Географиясе
    -0.48
     الاطلاع
    -0.47
     שוליים
    -0.46
    POSITIVE LOGITS
    argout
    0.44
     recap
    0.43
     Participation
    0.42
     participation
    0.41
    PyTuple
    0.40
     relive
    0.40
     retrospect
    0.39
     hindsight
    0.38
     reca
    0.38
    Participation
    0.38
    Act Density 0.027%

    No Known Activations