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

    Neuronpedia

    INDEX
    Explanations

    gender

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     вже
    -0.07
    解决
    -0.07
     uw
    -0.06
     �
    -0.06
     sudoku
    -0.06
    amaha
    -0.06
    -ни
    -0.06
    igsaw
    -0.06
    ічні
    -0.06
    (dy
    -0.06
    POSITIVE LOGITS
     overlook
    0.07
     применения
    0.07
     startTime
    0.06
     withObject
    0.06
                        
↵
    0.06
    レビ
    0.06
     projection
    0.06
     Fourth
    0.06
     calling
    0.06
     gimm
    0.06
    Act Density 0.015%

    No Known Activations