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

    Neuronpedia

    INDEX
    Explanations

    provided

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    igrams
    -0.07
     kon
    -0.06
     ś
    -0.06
     Converted
    -0.06
    ังส
    -0.06
     시간
    -0.06
    �
    -0.06
    _inter
    -0.06
     ℝ
    -0.06
    認
    -0.06
    POSITIVE LOGITS
     hopefully
    0.07
    aget
    0.06
     PLAY
    0.06
    SPORT
    0.06
     SET
    0.06
     trp
    0.06
     disponibles
    0.06
     maur
    0.06
    费
    0.06
    _changed
    0.06
    Act Density 0.027%

    No Known Activations