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

    Neuronpedia

    INDEX
    Explanations

    code termination punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    たちは
    0.43
    雖然
    0.42
    ?),
    0.40
    ...),
    0.39
    ²)
    0.39
    ※
    0.39
    */)
    0.39
    )$,
    0.39
    たちの
    0.39
    들은
    0.38
    POSITIVE LOGITS
    ;
    0.90
    ؛
    0.75
    ；
    0.74
    ;.
    0.71
    ();
    0.71
    .;
    0.66
    ;}
    0.66
    ﹔
    0.63
    ;"
    0.61
    ;\
    0.61
    Act Density 0.023%

    No Known Activations