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

    Neuronpedia

    INDEX
    Explanations

    course

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    销
    -0.07
     zx
    -0.07
    из
    -0.07
    мор
    -0.07
     recommended
    -0.07
    败
    -0.07
    ә
    -0.07
     microseconds
    -0.07
    区域
    -0.07
    辨
    -0.07
    POSITIVE LOGITS
     clar
    0.08
    -trained
    0.07
     Теп
    0.07
     cv
    0.07
    (',')[
    0.07
    -stats
    0.07
    Pers
    0.07
    ,cv
    0.07
     stepping
    0.07
    	cv
    0.07
    Act Density 0.564%

    No Known Activations