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

    Neuronpedia

    INDEX
    Explanations

    exposure to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    يل
    0.97
    ية
    0.87
    শোধ
    0.86
    న్
    0.83
    לו
    0.83
    ině
    0.80
    вая
    0.79
    ше
    0.79
    يس
    0.78
    chées
    0.78
    POSITIVE LOGITS
     exposure
    1.31
    Exposure
    1.13
     Exposure
    1.11
    i
    1.00
    '
    1.00
     exposures
    0.91
    ↵↵
    0.87
    t
    0.86
     expos
    0.85
    exposure
    0.84
    Act Density 0.009%

    No Known Activations