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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and expressions

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

    Mathematical symbols after a dollar sign

    np_acts-logits-general · gemini-2.0-flash

    mathematical notation and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     يتيمه
    -0.89
    principalTable
    -0.72
     NDL
    -0.71
    endes
    -0.70
     Mendes
    -0.70
    es
    -0.68
    }{-
    -0.68
     دیکھیے
    -0.68
     Cordero
    -0.68
    eis
    -0.66
    POSITIVE LOGITS
    "\
    0.98
     \
    0.93
    $\
    0.90
     ($\
    0.83
    #\
    0.83
    avut
    0.81
    middels
    0.81
    ("\
    0.79
     "\
    0.77
     [\
    0.76
    Act Density 0.168%

    No Known Activations