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

    Neuronpedia

    INDEX
    Explanations

    cars

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Erl
    -0.08
    侣
    -0.08
     során
    -0.07
    little
    -0.07
     neurological
    -0.07
    Deaths
    -0.07
    oust
    -0.07
     vinc
    -0.07
    caire
    -0.07
    цы
    -0.07
    POSITIVE LOGITS
    ًا
    0.09
     garages
    0.08
     bumper
    0.08
     ott
    0.08
    اً
    0.08
    ச்
    0.08
    �
    0.07
     Calvin
    0.07
     الاث
    0.07
     विन
    0.07
    Act Density 0.001%

    No Known Activations