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

    Neuronpedia

    INDEX
    Explanations

    movement and direction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Ее
    2.00
     लड़ा
    1.93
     Еще
    1.89
     Cozy
    1.73
    著者
    1.73
     учета
    1.71
     جميعا
    1.69
     ее
    1.68
     наличие
    1.68
    ের
    1.66
    POSITIVE LOGITS
    ない
    2.70
    ك
    2.16
    ان
    2.13
    at
    2.11
    ないと
    2.09
    uje
    2.06
    ieties
    1.98
    ias
    1.91
    বেগ
    1.90
    下旬
    1.90
    Act Density 0.198%

    No Known Activations