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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Lydia
    -0.07
    ulti
    -0.07
    魏
    -0.07
     Mend
    -0.06
     Maurice
    -0.06
    “The
    -0.06
    姤
    -0.06
     nextProps
    -0.06
     신
    -0.06
    mlink
    -0.06
    POSITIVE LOGITS
    我们必须
    0.07
    (_.
    0.07
    Raster
    0.07
     저는
    0.07
    各種
    0.07
    _personal
    0.07
     labore
    0.06
    [res
    0.06
     jars
    0.06
     kans
    0.06
    Act Density 0.001%

    No Known Activations