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

    Neuronpedia

    INDEX
    Explanations

    subjects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ка
    0.90
    ك
    0.84
    ल
    0.84
    ل
    0.78
    م
    0.77
    ز
    0.77
    ม
    0.75
    де
    0.72
    л
    0.71
    ک
    0.71
    POSITIVE LOGITS
    ènes
    0.59
    0.59
     Handsome
    0.56
    0.56
    Keep
    0.56
     campione
    0.55
    Bear
    0.55
     நாம்
    0.55
    Trial
    0.55
     craftsman
    0.55
    Act Density 0.001%

    No Known Activations