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

    Neuronpedia

    INDEX
    Explanations

    service

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    研学
    -0.07
     bfs
    -0.07
     Council
    -0.07
    asc
    -0.06
    润
    -0.06
     joy
    -0.06
    MP
    -0.06
    �
    -0.06
    还想
    -0.06
    赈
    -0.06
    POSITIVE LOGITS
    upplier
    0.08
    iping
    0.07
    时刻
    0.07
    idenav
    0.07
    idian
    0.07
    	delay
    0.07
     Natalie
    0.07
    脸色
    0.07
    Locale
    0.07
    blas
    0.06
    Act Density 0.006%

    No Known Activations