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

    Neuronpedia

    INDEX
    Explanations

    twinkle, include, exclude

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ä
    1.01
    af
    0.91
    ים
    0.91
    ə
    0.90
    ong
    0.88
     마
    0.86
    ts
    0.84
     مشکل
    0.83
     समस्याएं
    0.80
    ENT
    0.79
    POSITIVE LOGITS
    ن
    1.43
    ন
    1.27
    ↵↵
    1.25
    न
    1.25
    ו
    1.25
    <0x80>
    1.22
    n
    1.22
    ;
    1.18
    น
    1.13
    Y
    1.13
    Act Density 0.000%

    No Known Activations