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

    Neuronpedia

    INDEX
    Explanations

    mm

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     spi
    -0.06
     né
    -0.06
    。しかし
    -0.06
     lands
    -0.06
    _survey
    -0.06
     reb
    -0.06
    按钮
    -0.06
    げ
    -0.06
    Fuel
    -0.06
    Icons
    -0.06
    POSITIVE LOGITS
     Bbw
    0.07
     Tf
    0.07
    ♪
    0.07
     Candle
    0.07
    came
    0.07
     •
    0.07
    mmm
    0.06
     yummy
    0.06
    acağını
    0.06
     absorb
    0.06
    Act Density 0.005%

    No Known Activations