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

    Neuronpedia

    INDEX
    Explanations

    is are

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     кар
    -0.07
    智
    -0.06
    違
    -0.06
     HWND
    -0.06
     afflict
    -0.06
     Charles
    -0.06
    -thumb
    -0.06
    	DEBUG
    -0.06
    .between
    -0.06
    rists
    -0.06
    POSITIVE LOGITS
    ты
    0.07
     lowered
    0.07
    .assertIs
    0.07
    اران
    0.07
     }}"></
    0.06
     Hole
    0.06
    <!--<
    0.06
    perimental
    0.06
     multer
    0.06
     historia
    0.06
    Act Density 0.101%

    No Known Activations