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

    Neuronpedia

    INDEX
    Explanations

    numerical data or statistics

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

    numbers and digits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RectangleBorder
    -0.69
     VIDEOT
    -0.57
    bender
    -0.57
     препратки
    -0.54
    adaptiveStyles
    -0.54
    NameValuePair
    -0.54
    carus
    -0.53
     EconPapers
    -0.52
    GTCX
    -0.52
     stabilisation
    -0.52
    POSITIVE LOGITS
     soixante
    0.60
     Sixty
    0.60
     Seventy
    0.59
     cinquante
    0.55
     sixty
    0.53
     seventy
    0.53
     cincuenta
    0.50
     eighty
    0.49
    Sixty
    0.49
     Fifty
    0.49
    Act Density 0.825%

    No Known Activations