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

    Neuronpedia

    INDEX
    Explanations

    fully

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tall
    -0.08
     VW
    -0.07
    /string
    -0.06
    Also
    -0.06
     درجة
    -0.06
     CW
    -0.06
    ieu
    -0.06
     Oil
    -0.06
     Thirty
    -0.06
    _AG
    -0.06
    POSITIVE LOGITS
     fully
    0.08
     çal
    0.07
     maintain
    0.07
     tách
    0.06
    	cp
    0.06
     sum
    0.06
     coverage
    0.06
    안마
    0.06
     maintaining
    0.06
     Completely
    0.06
    Act Density 0.017%

    No Known Activations