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

    Neuronpedia

    INDEX
    Explanations

    specific discourse types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    DanhMucSP
    0.38
    太阳
    0.37
     Soleil
    0.37
    riek
    0.36
    RAchievement
    0.36
     tř
    0.35
     плодо
    0.35
     shears
    0.34
     fins
    0.34
     रखकर
    0.34
    POSITIVE LOGITS
     impressively
    0.42
    摳
    0.39
    ம்ப
    0.39
     impressive
    0.38
    ಮೆ
    0.38
     hogs
    0.37
     (--
    0.37
    컸
    0.37
    ees
    0.37
     BIOS
    0.37
    Act Density 0.000%

    No Known Activations