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

    Neuronpedia

    INDEX
    Explanations

    World

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    __$
    -0.07
     объем
    -0.06
    $↵↵
    -0.06
    fon
    -0.06
    동안
    -0.06
    	dx
    -0.06
     mux
    -0.06
    руб
    -0.06
    質
    -0.06
     Tall
    -0.06
    POSITIVE LOGITS
    Concrete
    0.07
     мере
    0.07
    днання
    0.06
    Patient
    0.06
    갔다
    0.06
     continuar
    0.06
    _prog
    0.06
    技术
    0.06
    Orden
    0.06
    976
    0.06
    Act Density 0.010%

    No Known Activations