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

    Neuronpedia

    INDEX
    Explanations

    categories and statistics related to demographic groups

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

    Text before numbers, symbols, or math

    np_acts-logits-general · gemini-2.0-flash

    sides, percentages, and true/false

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     }(\
    -0.62
    =#{
    -0.55
    NUMX
    -0.50
    "</
    -0.50
     gogh
    -0.49
    -0.49
    რ
    -0.47
    . 
    -0.47
    uſe
    -0.47
    ’
    -0.47
    POSITIVE LOGITS
    ↵↵
    1.21
    <eos>
    1.00
    ValueStyle
    0.88
    ↵↵↵
    0.83
    ↵
    0.82
    ↵↵↵↵
    0.80
    </h2>
    0.78
     complémentaires
    0.69
     nakalista
    0.68
    rungsseite
    0.68
    Act Density 0.420%

    No Known Activations