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

    Neuronpedia

    INDEX
    Explanations

    discussing issues or topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     such
    0.54
     diesen
    0.47
     enjeux
    0.45
    such
    0.44
    䚺
    0.44
    comme
    0.44
     takie
    0.43
    Buen
    0.43
    ऐसा
    0.43
     ऐसा
    0.43
    POSITIVE LOGITS
    ファイルの
    0.48
     боль
    0.47
     возможность
    0.46
     учетом
    0.46
     начинает
    0.45
     днев
    0.45
     связи
    0.44
     со
    0.44
     связь
    0.44
     память
    0.43
    Act Density 0.239%

    No Known Activations