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

    Neuronpedia

    INDEX
    Explanations

    random

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ATIONAL
    -0.09
     photographic
    -0.07
    rys
    -0.07
    epad
    -0.07
    veau
    -0.07
    speed
    -0.07
    RequestMethod
    -0.07
    四方
    -0.07
     Terrain
    -0.07
    Protocol
    -0.07
    POSITIVE LOGITS
    幸
    0.08
    坜
    0.07
     winger
    0.07
    داء
    0.07
    〚
    0.07
    SKI
    0.07
     sibling
    0.06
    <src
    0.06
    classnames
    0.06
     ≥
    0.06
    Act Density 0.024%

    No Known Activations