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

    Neuronpedia

    INDEX
    Explanations

    numbers and quantities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ك
    1.87
    ق
    1.58
    ض
    1.33
    ب
    1.31
    ম
    1.16
    ،
    1.16
    কে
    1.15
    லோச
    1.13
    بد
    1.13
    یت
    1.10
    POSITIVE LOGITS
    ри
    1.44
    리
    1.35
    ла
    1.13
    れている
    1.13
    ol
    1.02
    er
    0.99
    on
    0.96
    中
    0.96
    el
    0.95
    ಸ್
    0.91
    Act Density 0.201%

    No Known Activations