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

    Neuronpedia

    INDEX
    Explanations

    usability and usury

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    т
    1.18
     USA
    1.08
    екси
    0.97
    দূ
    0.96
    鎂
    0.93
    Madison
    0.93
    ت
    0.92
    ÍA
    0.91
     aisa
    0.89
     Cheese
    0.88
    POSITIVE LOGITS
    queda
    1.06
    ca
    1.03
    cić
    0.97
    cular
    0.95
    ser
    0.95
    htein
    0.91
    ceptible
    0.91
    chetta
    0.88
     皆
    0.88
    ಸಿ
    0.86
    Act Density 0.069%

    No Known Activations