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

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Actor
    -0.07
     activ
    -0.06
    販
    -0.06
    LOOR
    -0.06
    +W
    -0.06
    [T
    -0.06
    .median
    -0.06
     lined
    -0.06
     EACH
    -0.06
     periodically
    -0.06
    POSITIVE LOGITS
     SplashScreen
    0.07
    -br
    0.07
    <?
    0.06
    数学
    0.06
     спост
    0.06
     findViewById
    0.06
    server
    0.06
    _Construct
    0.06
    (sm
    0.06
    ,end
    0.06
    Act Density 0.017%

    No Known Activations