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

    Neuronpedia

    INDEX
    Explanations

    inherited

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     EVEN
    -0.07
    帝国
    -0.07
     دور
    -0.07
     joyful
    -0.06
    (Sprite
    -0.06
     eben
    -0.06
    .Split
    -0.06
    年代
    -0.06
     luxurious
    -0.06
     findBy
    -0.06
    POSITIVE LOGITS
    _Column
    0.07
     inertia
    0.07
    -effective
    0.07
    恒
    0.07
     Charleston
    0.06
     Brain
    0.06
    Practice
    0.06
    LinkedIn
    0.06
     ):
    0.06
    selectors
    0.06
    Act Density 0.003%

    No Known Activations