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

    Neuronpedia

    INDEX
    Explanations

    help

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bfd
    -0.07
    	auth
    -0.07
    MM
    -0.07
    这片
    -0.07
     rp
    -0.07
    ZX
    -0.07
    نج
    -0.07
    )^
    -0.06
    udd
    -0.06
     degree
    -0.06
    POSITIVE LOGITS
    自杀
    0.07
     enthusiasm
    0.07
    Links
    0.07
    �
    0.07
    徉
    0.06
     Sorted
    0.06
    癫痫
    0.06
    发热
    0.06
    과장
    0.06
     riv
    0.06
    Act Density 0.018%

    No Known Activations