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

    Neuronpedia

    INDEX
    Explanations

    proven

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     精
    -0.06
    ='{$
    -0.06
    Editor
    -0.06
     UIS
    -0.06
     районе
    -0.06
     Yeah
    -0.06
     случай
    -0.06
    _Menu
    -0.06
     �
    -0.06
     разом
    -0.06
    POSITIVE LOGITS
     proven
    0.17
     documented
    0.07
     Mun
    0.07
     tested
    0.07
    源
    0.07
     Mali
    0.06
     분
    0.06
     determined
    0.06
     '\"
    0.06
    -origin
    0.06
    Act Density 0.004%

    No Known Activations