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

    Neuronpedia

    INDEX
    Explanations

    format

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     brawl
    -0.07
     divert
    -0.07
    _Query
    -0.07
    Extend
    -0.07
     hind
    -0.06
    tiler
    -0.06
    ivé
    -0.06
     whites
    -0.06
    (CC
    -0.06
     SAMPLE
    -0.06
    POSITIVE LOGITS
    scanner
    0.06
     Recreation
    0.06
    ovala
    0.06
    */,↵
    0.06
     وهي
    0.06
     yp
    0.06
     gösteren
    0.06
    []){↵
    0.06
     cins
    0.05
    	has
    0.05
    Act Density 1.685%

    No Known Activations