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

    Neuronpedia

    INDEX
    Explanations

    essential, pseudo, lens, electoral

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    工作中
    0.43
    可通过
    0.41
     инициа
    0.40
    ланган
    0.40
    торин
    0.40
    쇤
    0.40
    )،
    0.39
    ಲ್ಯ
    0.39
    룀
    0.39
    ),[
    0.38
    POSITIVE LOGITS
    uto
    0.47
    je
    0.46
    ra
    0.46
    ho
    0.45
    ua
    0.44
    ye
    0.43
    ato
    0.41
     terrible
    0.41
     right
    0.40
    ba
    0.40
    Act Density 0.000%

    No Known Activations