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

    Neuronpedia

    INDEX
    Explanations

    acknowledging considerations and caveats

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    現在
    0.38
    {~
    0.35
    ="
    0.35
     bagi
    0.35
    _{
    0.34
     Dawn
    0.31
    \
    0.31
    ⠉
    0.31
    现在
    0.30
     Silent
    0.30
    POSITIVE LOGITS
     gracefully
    0.47
     graciously
    0.41
     constructively
    0.41
     wholeheartedly
    0.38
     mediante
    0.38
     gladly
    0.37
     gratefully
    0.36
     باتوں
    0.35
     yaparak
    0.35
     judicious
    0.35
    Act Density 0.131%

    No Known Activations