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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sudoku
    -0.07
    isp
    -0.07
     Cuisine
    -0.07
     Mohamed
    -0.07
    ้น
    -0.06
    )),
    -0.06
     فتح
    -0.06
    *@
    -0.06
    ]</
    -0.06
    _rot
    -0.06
    POSITIVE LOGITS
     escorte
    0.07
    继续
    0.07
    lamış
    0.06
     davidjl
    0.06
     عليك
    0.06
     speedy
    0.06
     Autos
    0.06
     tầm
    0.06
    lder
    0.06
    erge
    0.06
    Act Density 0.041%

    No Known Activations