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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and fractions

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

    mathematical formulas with greek letters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     обо
    -0.30
    AS
    -0.30
    MM
    -0.29
    MMM
    -0.27
     Bes
    -0.27
    MT
    -0.27
    #
    -0.27
    re
    -0.27
    ↵
    -0.27
    MC
    -0.26
    POSITIVE LOGITS
    ValueStyle
    0.82
     مرئيه
    0.81
     Einfluß
    0.77
    EndContext
    0.73
     dieſer
    0.69
    المناصب
    0.67
     dieſem
    0.65
    :]:
    0.65
     dieſen
    0.64
     ſeinem
    0.64
    Act Density 0.062%

    No Known Activations