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

    Neuronpedia

    INDEX
    Explanations

    the name David

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    टी
    1.23
    다고
    1.13
    고
    1.10
    র
    1.09
     on
    1.07
     труда
    1.02
    हदी
    1.02
    정이
    1.01
    ため
    0.97
    ந்த
    0.97
    POSITIVE LOGITS
    ك
    1.80
    c
    1.73
    ă
    1.59
    k
    1.55
    ing
    1.55
    า
    1.52
    ة
    1.51
    in
    1.47
    ı
    1.46
    n
    1.45
    Act Density 0.004%

    No Known Activations