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

    Neuronpedia

    INDEX
    Explanations

    joint operations and imports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     irrever
    0.63
    time
    0.61
     axons
    0.59
    ᐋ
    0.59
     necesit
    0.57
    by
    0.56
     deftly
    0.55
    رير
    0.54
    اد
    0.53
    ₂)
    0.53
    POSITIVE LOGITS
     میتوان
    0.54
     כ
    0.53
    с
    0.53
     πέ
    0.52
     Архиви
    0.52
     Π
    0.51
    >().
    0.50
     גם
    0.50
    otron
    0.49
    BD
    0.49
    Act Density 0.000%

    No Known Activations