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

    Neuronpedia

    INDEX
    Explanations

    journal citations and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Pierws
    0.79
    蹶
    0.73
    ાડ
    0.72
    чатку
    0.71
    Исход
    0.70
    攻擊
    0.70
     conoscenze
    0.69
     Gilles
    0.69
     parro
    0.69
    攻击
    0.69
    POSITIVE LOGITS
    supplement
    0.83
     SPECIAL
    0.80
     special
    0.77
    special
    0.76
     Special
    0.74
    September
    0.72
     Supplement
    0.72
     SUPPL
    0.70
     حصہ
    0.68
    SPECIAL
    0.68
    Act Density 0.011%

    No Known Activations