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

    Neuronpedia

    INDEX
    Explanations

    #

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    转换
    -0.07
     takes
    -0.07
    _CONF
    -0.07
    FFT
    -0.06
    퍅
    -0.06
    moving
    -0.06
     Workers
    -0.06
    Tu
    -0.06
    ⁈
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     Barrel
    0.07
    ⚗
    0.07
     Magical
    0.07
    国外
    0.07
    (up
    0.06
     boats
    0.06
    qx
    0.06
    Hours
    0.06
    很棒
    0.06
    Api
    0.06
    Act Density 0.001%

    No Known Activations