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

    Neuronpedia

    INDEX
    Explanations

    mathematical concepts and operations

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

    modulo 10

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     كومونز
    -0.73
    SourceChecksum
    -0.63
    GEBURTS
    -0.57
    adaptiveStyles
    -0.55
    TagMode
    -0.53
    Hentet
    -0.52
    OGND
    -0.52
     ComVisible
    -0.52
     CanadaChoose
    -0.50
     ligiloj
    -0.48
    POSITIVE LOGITS
    qrstuvwxyz
    0.44
     explotación
    0.41
    rektur
    0.41
    isdigit
    0.39
     Privacidade
    0.37
     nélkül
    0.36
    Schedulers
    0.36
    氓
    0.35
    fillType
    0.35
     madre
    0.35
    Act Density 0.043%

    No Known Activations