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

    Neuronpedia

    INDEX
    Explanations

    individuals adopting, reset the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    パ
    0.52
    事
    0.43
     사진
    0.43
    ष्
    0.42
    ק
    0.42
    アニメ
    0.41
    lensFlare
    0.40
    ハ
    0.40
     수상
    0.40
    cs
    0.40
    POSITIVE LOGITS
     İstifadə
    0.48
     reim
    0.43
     الذين
    0.43
     porttitor
    0.42
     defini
    0.42
     Lippincott
    0.42
    يم
    0.41
     нашим
    0.41
    Authorization
    0.40
     mandate
    0.40
    Act Density 0.008%

    No Known Activations