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

    Neuronpedia

    INDEX
    Explanations

    references to awards, nominations, and rankings within lists

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

    "best" or "top" lists

    np_acts-logits-general · gemini-2.0-flash

    best of the best lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     esternos
    -0.62
    genheit
    -0.57
     שוליים
    -0.57
    Билгалдахарш
    -0.55
     transfieras
    -0.55
    RenderAtEndOf
    -0.54
    PhysRevD
    -0.54
    SequentialGroup
    -0.54
    Искәрмәләр
    -0.54
    CloseOperation
    -0.52
    POSITIVE LOGITS
     best
    1.47
    best
    1.39
    Best
    1.38
     Best
    1.35
     top
    1.28
     Top
    1.22
     BEST
    1.19
    Top
    1.17
    BEST
    1.14
    top
    1.13
    Act Density 0.217%

    No Known Activations