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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions or equations involving variables and arithmetic operations

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

    Variables in algebraic equations

    np_acts-logits-general · gemini-2.0-flash

    equations with symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Chwiliwch
    -0.63
    Personendaten
    -0.62
    IsMutable
    -0.57
    Tikang
    -0.56
    pernicus
    -0.55
    rungsseite
    -0.54
     Meksiku
    -0.53
     ویکی‌پدیای
    -0.53
    +#+#
    -0.51
     تضيفلها
    -0.49
    POSITIVE LOGITS
    =-
    0.59
     (-
    0.57
     (−
    0.56
     negative
    0.56
     negativ
    0.54
    Negative
    0.52
    )=-\
    0.52
     $(-
    0.52
    Worse
    0.51
    negative
    0.50
    Act Density 2.296%

    No Known Activations