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

    Neuronpedia

    INDEX
    Explanations

    erythropoietin or erythrocyte

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    (
    1.00
    us
    0.95
    ul
    0.94
     can
    0.93
    os
    0.92
    ys
    0.91
    ou
    0.90
    et
    0.89
    z
    0.88
    л
    0.85
    POSITIVE LOGITS
    خ
    0.82
    你
    0.80
    خدم
    0.79
    내
    0.79
    ﺧ
    0.76
    ف
    0.75
    而
    0.73
    車
    0.72
    車の
    0.72
    내가
    0.71
    Act Density 0.008%

    No Known Activations