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

    Neuronpedia

    INDEX
    Explanations

    payment solutions and services

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ۔
    1.65
    は
    1.48
    는
    1.41
    لی
    1.40
    ot
    1.18
    ਰ
    1.17
    ።
    1.12
    ون
    1.11
    い
    1.09
    ।
    1.08
    POSITIVE LOGITS
    ल
    1.02
     payment
    0.95
     verwend
    0.90
     for
    0.89
     beho
    0.87
    е
    0.84
     paiement
    0.83
    л
    0.83
    Payment
    0.82
     Payment
    0.82
    Act Density 0.012%

    No Known Activations