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

    Neuronpedia

    INDEX
    Explanations

    past tense or adjective forms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ت
    1.09
    ל
    0.87
    т
    0.73
    ת
    0.71
    י
    0.70
    с
    0.69
    ات
    0.69
    و
    0.68
    л
    0.67
    सँग
    0.66
    POSITIVE LOGITS
    resolved
    0.55
    SE
    0.54
    一定的
    0.54
     Changed
    0.49
     था
    0.47
    ays
    0.46
     Warsz
    0.46
     {\
    0.46
     प्रस्तावित
    0.46
     å
    0.45
    Act Density 0.000%

    No Known Activations