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

    Neuronpedia

    INDEX
    Explanations

    Performance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Performance
    -0.71
    Performance
    -0.62
     PERFORMANCE
    -0.47
     kanssa
    -0.45
    HF
    -0.44
    UnknownFields
    -0.44
     HF
    -0.43
    Perf
    -0.41
    ed
    -0.41
    PreExecute
    -0.40
    POSITIVE LOGITS
     للمعارف
    0.85
     '\\;'
    0.84
     المعيارى
    0.77
     surla
    0.72
    Tembelea
    0.72
    Билгалдахарш
    0.71
    aarrggbb
    0.68
     مرئيه
    0.68
    Зноскі
    0.67
     snippetHide
    0.67
    Act Density 0.089%

    No Known Activations