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

    Neuronpedia

    INDEX
    Explanations

    geometric pairs and sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ে
    0.68
    ి
    0.66
    <0x0D>
    0.64
    t
    0.63
    n
    0.63
    i
    0.62
    ة
    0.57
    中
    0.56
    e
    0.55
    の
    0.55
    POSITIVE LOGITS
     ă
    0.60
     дві
    0.57
    ʍ
    0.52
     reiniciar
    0.51
    եր
    0.50
     ставить
    0.50
    ่า
    0.49
     symmetrically
    0.49
     cặp
    0.49
     daños
    0.49
    Act Density 0.000%

    No Known Activations