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

    Neuronpedia

    INDEX
    Explanations

    double

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Maia
    -0.08
     क्षमता
    -0.08
     cognitive
    -0.08
     estimation
    -0.08
     Cognitive
    -0.08
     cognition
    -0.07
     Cogn
    -0.07
     Kino
    -0.07
     Est
    -0.07
     gives
    -0.07
    POSITIVE LOGITS
     પડે
    0.10
     hurdles
    0.09
     તાર
    0.09
     થતાં
    0.09
     ddefnyddio
    0.08
     nuits
    0.08
     પડ
    0.08
     પડી
    0.08
    ાત
    0.08
    Wanted
    0.08
    Act Density 0.003%

    No Known Activations