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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    xlim
    -0.08
    見て
    -0.07
     решил
    -0.07
    ]int
    -0.07
    希望能够
    -0.06
     Canberra
    -0.06
     Allowed
    -0.06
     Manufacturers
    -0.06
    㹦
    -0.06
     richTextBox
    -0.06
    POSITIVE LOGITS
    阕
    0.07
    lates
    0.07
    节约
    0.07
     classNames
    0.07
    契
    0.07
    gements
    0.07
    -star
    0.07
    经销
    0.07
    InterfaceOrientation
    0.07
    ystery
    0.07
    Act Density 0.002%

    No Known Activations