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

    Neuronpedia

    INDEX
    Explanations

    numerical values relevant to data or statistics

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

    Fractions and ratios

    np_acts-logits-general · gemini-2.0-flash

    numbers and indices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -1.11
     resourceCulture
    -1.04
    */),
    -0.93
     ComVisible
    -0.90
     препратки
    -0.87
    ]='\
    -0.87
     تضيفلها
    -0.86
    .”—
    -0.85
     >(
    -0.84
    zzlies
    -0.84
    POSITIVE LOGITS
    2
    1.73
    nd
    1.09
    3
    1.06
    0
    1.04
    4
    1.01
    1
    0.98
    5
    0.95
    6
    0.81
    8
    0.80
    7
    0.80
    Act Density 1.520%

    No Known Activations