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

    Neuronpedia

    INDEX
    Explanations

    raw material

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Miniature
    0.49
    ＾＾
    0.48
    匯
    0.48
    ０
    0.43
     Tosc
    0.43
    澜
    0.43
     wonderful
    0.42
     extraordinaire
    0.41
     Towers
    0.41
     Wonderful
    0.41
    POSITIVE LOGITS
    arse
    0.54
    aciones
    0.53
     препят
    0.53
    aprendizaje
    0.51
    а
    0.49
    ных
    0.49
     массы
    0.48
     способы
    0.48
     объем
    0.48
     профилакти
    0.48
    Act Density 0.000%

    No Known Activations