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

    Neuronpedia

    INDEX
    Explanations

    rounding up, out, or method

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    t
    1.97
     to
    1.53
    ל
    1.41
    </h2>
    1.40
    ק
    1.39
    to
    1.30
    在
    1.29
    </u>
    1.27
     l
    1.27
    م
    1.23
    POSITIVE LOGITS
    ０
    1.12
     tròn
    0.98
     disponibilités
    0.97
    வ்வேறு
    0.95
    ensioni
    0.94
    OOOO
    0.93
     vutto
    0.92
    aitement
    0.92
    ambilan
    0.92
    ított
    0.91
    Act Density 0.000%

    No Known Activations