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

    Neuronpedia

    INDEX
    Explanations

    Col, col, and Kol prefixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ImageAlign
    0.43
    োক্ত
    0.42
    د
    0.41
    دخل
    0.38
    forcement
    0.38
    ungsl
    0.38
     perasaan
    0.37
    در
    0.37
    OLYBDENUM
    0.36
    ängel
    0.36
    POSITIVE LOGITS
    Col
    0.91
     col
    0.87
     Col
    0.83
     COL
    0.75
     коло
    0.73
     콜
    0.71
     colo
    0.70
    col
    0.68
     Kol
    0.66
     kol
    0.66
    Act Density 0.028%

    No Known Activations