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

    Neuronpedia

    INDEX
    Explanations

    De vanagari script, symbols, and repeated characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ה
    0.73
    д
    0.68
    a
    0.65
     greatest
    0.64
     pihak
    0.62
    Monday
    0.61
     впервые
    0.61
    erler
    0.61
     अधीन
    0.61
    轼
    0.60
    POSITIVE LOGITS
    ed
    0.71
    ా
    0.69
    ened
    0.64
    ansch
    0.64
    يين
    0.63
    יות
    0.60
    ду
    0.59
    orsky
    0.59
    ة
    0.59
    ationen
    0.57
    Act Density 0.051%

    No Known Activations