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

    Neuronpedia

    INDEX
    Explanations

    A velocity, A grep

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     populate
    0.41
     dtype
    0.38
     আন
    0.37
    populate
    0.37
     populated
    0.36
     arranged
    0.36
     đúng
    0.36
     supplements
    0.35
     Populate
    0.35
    監督
    0.35
    POSITIVE LOGITS
     Squire
    0.48
    र्श
    0.43
     McCle
    0.43
    Armstrong
    0.41
    ్లా
    0.39
    یشه
    0.38
     Lobkowicz
    0.38
    如果你
    0.38
    愿意
    0.38
    领域的
    0.37
    Act Density 0.000%

    No Known Activations