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

    Neuronpedia

    INDEX
    Explanations

    tech platform names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    و
    0.75
    ні
    0.57
    and
    0.50
    f
    0.48
    ни
    0.46
    for
    0.45
    ку
    0.45
    op
    0.45
    ك
    0.44
    bins
    0.43
    POSITIVE LOGITS
    কে
    0.43
     in
    0.41
    ט
    0.40
     to
    0.40
    ใน
    0.39
     pike
    0.39
     about
    0.39
     în
    0.38
     exfoliating
    0.38
     you
    0.38
    Act Density 0.227%

    No Known Activations