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

    Neuronpedia

    INDEX
    Explanations

    divide both sides

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Pct
    0.98
    ()/
    0.97
    Ảnh
    0.96
    LAGAB
    0.93
     Correctional
    0.93
    0.92
     oth
    0.92
     Màu
    0.91
     Athletes
    0.87
    сійскай
    0.87
    POSITIVE LOGITS
    '
    1.10
     polynomials
    1.05
    ی
    1.05
    ল
    0.97
     polynomial
    0.93
    ל
    0.92
    ণা
    0.91
    रु
    0.91
     bespoke
    0.90
    a
    0.90
    Act Density 0.539%

    No Known Activations