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

    Neuronpedia

    INDEX
    Explanations

    characters and symbols typically used in programming or markup languages

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

    start_of_turn user

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sust
    -0.42
    Diweddarwch
    -0.39
     cat
    -0.38
    InProgress
    -0.38
     Cat
    -0.38
     hor
    -0.37
    mobileqq
    -0.37
    labus
    -0.36
    baix
    -0.36
    Rujuakan
    -0.36
    POSITIVE LOGITS
     ModelExpression
    0.61
     resourceCulture
    0.52
    insegna
    0.50
     Audiodateien
    0.48
    LookAnd
    0.47
     <=",
    0.46
     مرئيه
    0.46
    GeoNames
    0.45
     gelukkig
    0.45
    AntiForgeryToken
    0.43
    Act Density 0.000%

    No Known Activations