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

    Neuronpedia

    INDEX
    Explanations

    blank

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Size
    -0.07
    eware
    -0.07
     Fusion
    -0.07
     Cost
    -0.07
     uncomfort
    -0.07
    edo
    -0.07
    Escape
    -0.07
    (sim
    -0.06
    луш
    -0.06
    累了
    -0.06
    POSITIVE LOGITS
     usable
    0.07
    _rotate
    0.07
    埵
    0.07
    哈哈
    0.07
    💷
    0.07
    ཆ
    0.07
     olacaktır
    0.07
    oooooooo
    0.07
    展开
    0.07
    indr
    0.07
    Act Density 0.005%

    No Known Activations