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
    (codec
    -0.07
    InInspector
    -0.07
    诗词
    -0.07
    롣
    -0.06
     İslam
    -0.06
     laz
    -0.06
     possui
    -0.06
     jylland
    -0.06
    自主创新
    -0.06
     Foundation
    -0.06
    POSITIVE LOGITS
     waterfront
    0.07
    onal
    0.07
    的感受
    0.07
    原則
    0.07
    UNIT
    0.07
    cery
    0.07
    شن
    0.07
     eliminates
    0.07
    玶
    0.06
     orient
    0.06
    Act Density 0.001%

    No Known Activations