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
    민주
    -0.07
     लड
    -0.07
    Fil
    -0.06
     فرض
    -0.06
    aln
    -0.06
    _DH
    -0.06
     accepts
    -0.06
    人类
    -0.06
     voir
    -0.06
    .ma
    -0.06
    POSITIVE LOGITS
    =''):↵
    0.06
     ${
    0.06
     пак
    0.06
     $(
    0.06
    	It
    0.06
    ="$(
    0.06
     граж
    0.06
    üh
    0.06
    iasco
    0.06
     embroidery
    0.06
    Act Density 0.007%

    No Known Activations