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

    Neuronpedia

    INDEX
    Explanations

    low quality or resolution

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     TIME
    0.46
     hög
    0.45
     其
    0.45
    لق
    0.44
     школи
    0.44
    高
    0.44
    $",
    0.44
    高い
    0.44
     Те
    0.44
     उच्च
    0.43
    POSITIVE LOGITS
     low
    1.18
    低
    1.05
     Low
    1.03
    Low
    1.02
     низ
    1.02
    LOW
    1.02
    low
    0.98
     LOW
    0.93
    低的
    0.93
     rendah
    0.89
    Act Density 0.041%

    No Known Activations