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

    Neuronpedia

    INDEX
    Explanations

    diagnose issues

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ")");
    0.53
    gling
    0.48
    parvec
    0.48
    W
    0.47
    Sebelum
    0.46
    Sis
    0.46
    kernel
    0.45
    ವರ
    0.45
    Swiss
    0.45
    དང་
    0.45
    POSITIVE LOGITS
     mingling
    0.52
    ä
    0.48
    োগ্য
    0.47
     Zuckerberg
    0.46
     lapses
    0.45
    驿
    0.45
     डू
    0.45
     مرتبط
    0.45
    ओं
    0.44
     renovations
    0.44
    Act Density 0.000%

    No Known Activations