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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ánu
    -0.08
    έν
    -0.07
    cran
    -0.07
    goo
    -0.06
    _CBC
    -0.06
    uyla
    -0.06
    mma
    -0.06
     مشک
    -0.06
    veloper
    -0.06
     sprayed
    -0.06
    POSITIVE LOGITS
    Council
    0.08
     Explanation
    0.07
     الجام
    0.07
     rematch
    0.07
     관련
    0.07
     insists
    0.07
    	children
    0.06
     II
    0.06
     restless
    0.06
    .spec
    0.06
    Act Density 0.053%

    No Known Activations