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

    Neuronpedia

    INDEX
    Explanations

    see/judge for yourself

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     svc
    -0.07
    BEST
    -0.06
     Carousel
    -0.06
     funct
    -0.06
    ädchen
    -0.06
    だよ
    -0.06
    ки
    -0.06
    mrt
    -0.06
    -La
    -0.06
    кас
    -0.06
    POSITIVE LOGITS
     blockers
    0.07
     attribute
    0.07
    .url
    0.07
     متحده
    0.06
     callers
    0.06
    omid
    0.06
    =""/>↵
    0.06
    ْد
    0.06
     attributes
    0.06
     "-"↵
    0.06
    Act Density 0.019%

    No Known Activations