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

    Neuronpedia

    INDEX
    Explanations

    wide

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    结
    -0.07
    ества
    -0.07
    クラ
    -0.07
    agnost
    -0.06
     Connectivity
    -0.06
     quadrant
    -0.06
     manos
    -0.06
     дані
    -0.06
    fname
    -0.06
     znal
    -0.06
    POSITIVE LOGITS
    "-
    0.07
     Nie
    0.06
     illeg
    0.06
    "..
    0.06
     tc
    0.06
     Or
    0.06
     ")
    0.06
    urve
    0.06
     �
    0.06
    _PROC
    0.06
    Act Density 0.019%

    No Known Activations