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

    Neuronpedia

    INDEX
    Explanations

    News articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     identical
    -0.07
     труд
    -0.07
     neredeyse
    -0.07
     알려
    -0.06
    Researchers
    -0.06
    им
    -0.06
     �
    -0.06
     않
    -0.06
     Filipino
    -0.06
    坪
    -0.06
    POSITIVE LOGITS
    Pixel
    0.07
     uw
    0.07
    XXXX
    0.06
    Ý
    0.06
    [S
    0.06
    ãn
    0.06
    ý
    0.06
    	ac
    0.06
    _inst
    0.06
     Winston
    0.06
    Act Density 0.027%

    No Known Activations