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

    Neuronpedia

    INDEX
    Explanations

    Programming-related text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     trải
    -0.08
     tộc
    -0.07
    Plane
    -0.07
     rewarding
    -0.07
    -reference
    -0.07
    та
    -0.07
     blink
    -0.07
     initi
    -0.06
     dup
    -0.06
     undergo
    -0.06
    POSITIVE LOGITS
    书记
    0.07
    無し
    0.07
    _ver
    0.06
    /facebook
    0.06
     mơ
    0.06
     Clears
    0.06
    _CYCLE
    0.06
    autoreleasepool
    0.06
     ();
↵
    0.06
     gyr
    0.06
    Act Density 0.031%

    No Known Activations