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

    Neuronpedia

    INDEX
    Explanations

    references to scientific authors or citations in research literature

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

    citation surnames

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ‍♂️
    -0.48
    ‍♀️
    -0.46
     coming
    -0.45
     topping
    -0.44
     Fun
    -0.42
    coming
    -0.42
     Coming
    -0.42
     fain
    -0.41
    FUN
    -0.41
    хьтан
    -0.41
    POSITIVE LOGITS
     Exactos
    0.67
    IsContent
    0.59
     Administrativna
    0.55
    <?
    0.53
     Wikiseite
    0.47
     enfans
    0.47
     >=",
    0.45
     onCancelled
    0.45
    ----</
    0.44
     الحره
    0.44
    Act Density 0.593%

    No Known Activations