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

    Neuronpedia

    INDEX
    Explanations

    specific titles or choices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     núi
    0.49
     bảng
    0.49
    TH
    0.49
     và
    0.47
    떡
    0.46
    ен
    0.46
     Cush
    0.46
     tên
    0.45
     thứ
    0.45
    ,”
    0.43
    POSITIVE LOGITS
     ضرورت
    0.45
     Requires
    0.44
     hvil
    0.43
     ਤੁਸੀਂ
    0.42
    utilisation
    0.41
     necess
    0.40
    Unfortunately
    0.40
    ibre
    0.39
    配置
    0.39
     χρει
    0.38
    Act Density 0.000%

    No Known Activations