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

    Neuronpedia

    INDEX
    Explanations

    code/math

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Up
    -0.07
    pike
    -0.07
    odef
    -0.07
    ギ
    -0.06
     quadrant
    -0.06
    liste
    -0.06
    Bu
    -0.06
     Cha
    -0.06
     trận
    -0.06
     Buccaneers
    -0.06
    POSITIVE LOGITS
     then
    0.06
    少し
    0.06
     Pocket
    0.06
    ıydı
    0.06
     tranny
    0.06
     hry
    0.06
    igits
    0.06
     Gratis
    0.06
    .enemy
    0.06
    어
    0.06
    Act Density 0.000%

    No Known Activations