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

    Neuronpedia

    INDEX
    Explanations

    code structure or programming syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    の
    0.67
    of
    0.67
    U
    0.65
     של
    0.64
    ൈ
    0.64
    ۲
    0.64
    í
    0.64
    ُ
    0.63
     of
    0.61
    が
    0.61
    POSITIVE LOGITS
    ，
    0.84
     alebo
    0.67
    ).
    0.66
    ،
    0.65
     hoặc
    0.62
    .
    0.59
    ),
    0.57
    ↵↵
    0.55
     veya
    0.54
    ↵
    0.53
    Act Density 0.312%

    No Known Activations