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

    Neuronpedia

    INDEX
    Explanations

    global society

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	valid
    -0.06
    icamente
    -0.06
    umlu
    -0.06
    ，如果
    -0.06
    оба
    -0.06
    ulant
    -0.06
    tractive
    -0.06
    )?.
    -0.06
    λου
    -0.06
     cel
    -0.06
    POSITIVE LOGITS
    책
    0.07
     групп
    0.06
    Clientes
    0.06
     sitios
    0.06
    -rec
    0.06
     인천
    0.06
    .SET
    0.06
    .Ge
    0.06
     FUNC
    0.06
     Wanted
    0.06
    Act Density 0.066%

    No Known Activations