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

    Neuronpedia

    INDEX
    Explanations

    flavor

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     положительн
    -0.07
     дал
    -0.07
    _choose
    -0.07
    -dist
    -0.07
     이것은
    -0.07
    冲洗
    -0.06
    ِ
    -0.06
    在这种
    -0.06
    aes
    -0.06
    斗争
    -0.06
    POSITIVE LOGITS
     flavor
    0.08
    卮
    0.08
    关乎
    0.07
     Flavor
    0.07
    빋
    0.07
    嚓
    0.06
     flavored
    0.06
    trusted
    0.06
    招商
    0.06
    robot
    0.06
    Act Density 0.007%

    No Known Activations