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

    Neuronpedia

    INDEX
    Explanations

    numbers and characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ピンク
    0.49
     クリーム
    0.44
     PINK
    0.43
     abrió
    0.43
     অটো
    0.43
    ជន
    0.43
    廣場
    0.43
     CREAM
    0.42
    惱
    0.42
    ワイト
    0.42
    POSITIVE LOGITS
    лығы
    0.41
    dehyde
    0.39
    ıll
    0.39
    kova
    0.39
    amd
    0.38
    slu
    0.38
    ığ
    0.38
    antes
    0.37
    стве
    0.37
    sta
    0.36
    Act Density 0.004%

    No Known Activations