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

    Neuronpedia

    INDEX
    Explanations

    result

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    اسه
    -0.07
    ていない
    -0.07
     ttk
    -0.07
    Triangle
    -0.06
    距
    -0.06
    ListView
    -0.06
    itas
    -0.06
    ระ
    -0.06
    斗
    -0.06
     Bearings
    -0.06
    POSITIVE LOGITS
     فض
    0.08
     freel
    0.07
    Ont
    0.07
    .hasMore
    0.07
     senate
    0.07
     Beh
    0.07
     Fab
    0.06
     unless
    0.06
     talent
    0.06
    ώρα
    0.06
    Act Density 0.025%

    No Known Activations