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

    Neuronpedia

    INDEX
    Explanations

    references to mathematical concepts and terminology

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

    math

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    帖最后由
    -0.76
    Manbalar
    -0.68
    parsedMessage
    -0.66
     mergeFrom
    -0.66
     resourceCulture
    -0.65
     nahilalakip
    -0.63
    OGND
    -0.62
    رشف
    -0.60
    StoreMessageInfo
    -0.60
    flashdata
    -0.60
    POSITIVE LOGITS
     mathematics
    0.99
     math
    0.93
     maths
    0.88
     Mathematics
    0.87
     mathematical
    0.85
    Mathematics
    0.82
     Matem
    0.78
     MATHEMATICS
    0.77
    mathematics
    0.77
     Maths
    0.76
    Act Density 0.040%

    No Known Activations