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

    Neuronpedia

    INDEX
    Explanations

    defer cleanup actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ટ
    0.97
    特色
    0.95
     оформления
    0.89
    ون
    0.88
    ای
    0.88
    霑
    0.87
    Circ
    0.84
    ページ
    0.84
     حروف
    0.83
    B
    0.83
    POSITIVE LOGITS
    ended
    0.91
     ਹ
    0.87
    是一種
    0.87
     WndProc
    0.82
     Поэтому
    0.81
     Dub
    0.78
    ANAL
    0.78
     eus
    0.78
     Ya
    0.77
     inim
    0.77
    Act Density 0.002%

    No Known Activations