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

    Neuronpedia

    INDEX
    Explanations

    DATA segments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     못한
    0.40
    的大小
    0.39
    でない
    0.39
     nhiều
    0.38
    🈶
    0.38
     BOARDSIZE
    0.38
    ία
    0.38
    χή
    0.38
    痣
    0.38
    上的
    0.38
    POSITIVE LOGITS
    Mind
    0.44
    patri
    0.43
     Christendom
    0.42
    lovely
    0.42
    Lovely
    0.40
     entrust
    0.40
     അമേരിക്ക
    0.40
     penit
    0.40
    پ
    0.39
     الشرق
    0.39
    Act Density 0.000%

    No Known Activations