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

    Neuronpedia

    INDEX
    Explanations

    mathematical equations/code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    world
    -0.08
     egt
    -0.07
    setBackground
    -0.07
     tucked
    -0.06
     khởi
    -0.06
    άλυ
    -0.06
     hairst
    -0.06
    -fired
    -0.06
    нему
    -0.06
    thread
    -0.06
    POSITIVE LOGITS
     interpreted
    0.07
     winters
    0.06
    (vertical
    0.06
    _PROD
    0.06
    sock
    0.06
     få
    0.06
    обще
    0.06
    .Graphics
    0.06
     abl
    0.06
    。(
    0.06
    Act Density 0.002%

    No Known Activations