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

    Neuronpedia

    INDEX
    Explanations

    coding methods

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ABSPATH
    -0.07
     ngắn
    -0.06
     golf
    -0.06
    假
    -0.06
     segundos
    -0.06
    рут
    -0.06
     yas
    -0.06
     spanking
    -0.06
    UserService
    -0.06
    	Camera
    -0.06
    POSITIVE LOGITS
    ingu
    0.06
     orta
    0.06
     cnn
    0.06
     jednot
    0.06
    phia
    0.06
    _GAIN
    0.06
     Cumhuriyeti
    0.06
    hw
    0.06
    )?$
    0.06
    ніч
    0.06
    Act Density 0.013%

    No Known Activations