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

    Neuronpedia

    INDEX
    Explanations

    texture classification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    unun
    0.44
    ied
    0.43
    ago
    0.41
    clickable
    0.40
    anh
    0.40
    iknya
    0.40
    หรือไม่
    0.40
    edic
    0.38
     ότι
    0.38
    vem
    0.38
    POSITIVE LOGITS
     recorr
    0.46
    ع
    0.45
    职称
    0.40
     বিপরীতে
    0.40
    ually
    0.39
    Singolare
    0.39
    ='$
    0.39
    പ്പി
    0.39
    нинград
    0.39
    偃
    0.38
    Act Density 0.021%

    No Known Activations