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

    Neuronpedia

    INDEX
    Explanations

    numerical values and counts

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

    numbers followed by time units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     intptr
    -0.32
    esehen
    -0.31
     Selanjutnya
    -0.29
     marche
    -0.28
     ingår
    -0.28
     résulte
    -0.28
     mijne
    -0.27
     patří
    -0.27
     lenker
    -0.27
     elä
    -0.27
    POSITIVE LOGITS
    parsedMessage
    0.64
     $_(
    0.64
    ⟬
    0.63
    dozen
    0.63
     years
    0.62
    TargetException
    0.62
     CURIAM
    0.61
     weeks
    0.61
    URLException
    0.60
     $_"
    0.60
    Act Density 0.034%

    No Known Activations