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

    Neuronpedia

    INDEX
    Explanations

    say "na"

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     na
    2.34
    な
    1.87
    Na
    1.52
     Na
    1.49
     на
    1.36
    na
    1.36
     な
    1.29
     ना
    1.26
     نا
    1.20
     NA
    1.16
    POSITIVE LOGITS
    Мі
    0.39
     Nonlinear
    0.36
     Neighborhood
    0.36
     Pitts
    0.36
    atically
    0.35
    mium
    0.35
    ट्टी
    0.35
    かれている
    0.34
    ிகளில்
    0.34
     जिनको
    0.34
    Act Density 0.000%

    No Known Activations