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

    Neuronpedia

    INDEX
    Explanations

    Leaving

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    见
    -0.08
    ﹤
    -0.07
    tg
    -0.07
     applications
    -0.07
     induced
    -0.06
    Pr
    -0.06
     PRE
    -0.06
    زو
    -0.06
     bigger
    -0.06
    up
    -0.06
    POSITIVE LOGITS
    没办法
    0.07
     שאני
    0.07
    .class
    0.07
     CBS
    0.07
     ***↵
    0.07
    连忙
    0.07
     CNN
    0.06
    	ff
    0.06
     OPTIONAL
    0.06
    솝
    0.06
    Act Density 0.062%

    No Known Activations