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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and symbols

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

    Mathematical expressions, especially fractions

    np_acts-logits-general · gemini-2.0-flash

    mathematical equations and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.85
    '},
    -0.76
     autorytatywna
    -0.72
    úsqueda
    -0.70
    !")
    -0.69
    AsUp
    -0.69
    Autoritní
    -0.67
    клопе
    -0.67
    leſs
    -0.67
    rungsseite
    -0.67
    POSITIVE LOGITS
     =
    1.09
    =
    1.02
     $=
    0.69
     which
    0.67
    =\
    0.64
    ↵↵
    0.64
    =(
    0.63
    }=
    0.62
    Hentet
    0.59
     Thus
    0.58
    Act Density 0.629%

    No Known Activations