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

    Neuronpedia

    INDEX
    Explanations

    alpha, Expenses, <-

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     الساعه
    0.86
    messe
    0.74
    виси
    0.73
    꺼
    0.73
    щем
    0.73
    ant
    0.72
     bav
    0.71
    F
    0.70
    anatom
    0.69
    orn
    0.68
    POSITIVE LOGITS
    .-(
    0.81
    ؍
    0.81
    .—
    0.80
     destacó
    0.77
     ():
    0.76
    ：（
    0.74
     reacted
    0.73
    .--
    0.73
     .-
    0.72
     ዓይነት
    0.72
    Act Density 0.000%

    No Known Activations