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

    Neuronpedia

    INDEX
    Explanations

    same

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    nelles
    0.86
    ského
    0.83
    小于
    0.82
    ದ್ಧ
    0.78
    完整的
    0.76
    一组
    0.76
     প্রায়
    0.76
    完整
    0.76
    几乎
    0.74
     rotacao
    0.73
    POSITIVE LOGITS
     same
    1.42
     alike
    1.33
     mismo
    1.24
    same
    1.15
     même
    1.09
     mesma
    1.08
     mesmo
    1.07
     misma
    1.07
    Same
    1.02
     mismos
    1.02
    Act Density 0.005%

    No Known Activations