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

    Neuronpedia

    INDEX
    Explanations

    disclaimers and notes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ?),
    0.48
    ？」
    0.43
    ?"
    0.42
    这就
    0.42
    进而
    0.42
    ?—
    0.40
    ?'
    0.40
    ?-
    0.39
    ?»
    0.39
     Whether
    0.38
    POSITIVE LOGITS
    .):
    0.80
     unless
    0.75
     nhé
    0.64
    ですので
    0.64
     please
    0.63
    ):
    0.62
    .]:
    0.62
     Please
    0.61
    Please
    0.61
    입니다
    0.61
    Act Density 0.044%

    No Known Activations