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
     cameras
    -0.07
     Adj
    -0.07
     мод
    -0.07
    킨
    -0.06
    _learn
    -0.06
    緊
    -0.06
    显
    -0.06
    	no
    -0.06
    	TokenName
    -0.06
    영어
    -0.06
    POSITIVE LOGITS
     Percy
    0.07
     Beet
    0.06
    шие
    0.06
    %%↵
    0.06
    .Butter
    0.06
     ارزش
    0.06
    cin
    0.06
     Marx
    0.06
    $return
    0.06
    Vertices
    0.06
    Act Density 0.002%

    No Known Activations