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

    Neuronpedia

    INDEX
    Explanations

    beliefs and points of view

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     curvature
    -0.08
    ificent
    -0.07
    气温
    -0.07
     th
    -0.07
    ביץ
    -0.07
    近视
    -0.07
    Expect
    -0.07
    通り
    -0.06
     currentIndex
    -0.06
    ubble
    -0.06
    POSITIVE LOGITS
    -alone
    0.08
     cine
    0.07
     På
    0.07
     succes
    0.07
    剁
    0.07
    臺南
    0.07
    벴
    0.07
     date
    0.07
     extraordinary
    0.06
     Verfügung
    0.06
    Act Density 0.032%

    No Known Activations