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

    Neuronpedia

    INDEX
    Explanations

    following punctuation or Chinese words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Unit
    0.54
     Units
    0.49
    ikin
    0.48
     ताब
    0.47
     S
    0.47
    }
    0.47
     Shao
    0.46
    órm
    0.46
    }_{\
    0.45
     Vector
    0.45
    POSITIVE LOGITS
    う
    0.53
     moods
    0.47
    バー
    0.45
    を受ける
    0.44
     aisl
    0.44
    🙏
    0.44
    펀
    0.44
    १८
    0.43
     comed
    0.43
    周囲
    0.43
    Act Density 0.000%

    No Known Activations