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

    Neuronpedia

    INDEX
    Explanations

    tokenization system

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    多数
    0.41
    一
    0.41
    ُ
    0.40
     ]:
    0.40
    ](
    0.40
    rógeno
    0.40
     。
    0.39
    。。
    0.39
    :][
    0.38
    ㅕ
    0.38
    POSITIVE LOGITS
     elizabeth
    0.58
     Usa
    0.54
     diffe
    0.53
     informative
    0.51
     keepsake
    0.49
     cory
    0.48
     unmarried
    0.46
     cy
    0.46
     Ainsi
    0.46
     usa
    0.45
    Act Density 0.001%

    No Known Activations