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

    Neuronpedia

    INDEX
    Explanations

    needed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hiểu
    0.49
     कुत्रा
    0.45
     muchos
    0.44
     muitos
    0.43
    पेक्षा
    0.43
     pouvoir
    0.41
     Muitos
    0.41
     이해
    0.41
     河
    0.41
    україн
    0.41
    POSITIVE LOGITS
     Waalaikumsalam
    0.53
    उनके
    0.45
    返回值
    0.45
    isEmpty
    0.44
    row
    0.43
    rename
    0.42
    exit
    0.42
    ّد
    0.42
    k
    0.42
    result
    0.42
    Act Density 0.087%

    No Known Activations