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

    Neuronpedia

    INDEX
    Explanations

    sesame

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .FullName
    -0.07
    quelle
    -0.07
     Qgs
    -0.07
     år
    -0.07
     attends
    -0.06
    bben
    -0.06
     incarn
    -0.06
     Boss
    -0.06
    Ross
    -0.06
    Doc
    -0.06
    POSITIVE LOGITS
    סות
    0.07
    睬
    0.07
     דורש
    0.07
    צליח
    0.07
    .carousel
    0.07
    业界
    0.06
    trl
    0.06
     대통령
    0.06
     đến
    0.06
    versible
    0.06
    Act Density 0.001%

    No Known Activations