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

    Neuronpedia

    INDEX
    Explanations

    bash "rm" command

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bigger
    -0.06
    勝
    -0.06
     처음
    -0.06
    _growth
    -0.06
     podium
    -0.06
     brand
    -0.06
    짓
    -0.06
     mosques
    -0.06
     minorities
    -0.06
     wurden
    -0.06
    POSITIVE LOGITS
     Pied
    0.07
    @c
    0.07
    [X
    0.06
    وف
    0.06
    К
    0.06
     Pak
    0.06
     klin
    0.06
     %↵
    0.06
     dracon
    0.06
     penal
    0.06
    Act Density 0.006%

    No Known Activations