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

    Neuronpedia

    INDEX
    Explanations

    figure out

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ある
    1.01
    િ
    0.98
    hình
    0.93
    ВС
    0.91
    ട്ടില്‍
    0.91
     وما
    0.91
    ありますが
    0.88
    recyclerView
    0.88
    当我
    0.86
    Ngoài
    0.85
    POSITIVE LOGITS
     out
    1.78
     outwe
    1.08
     prominently
    1.06
     Out
    0.96
     crime
    0.92
    낸
    0.91
    낼
    0.90
    lijk
    0.90
     plt
    0.85
     somew
    0.85
    Act Density 0.005%

    No Known Activations