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

    Neuronpedia

    INDEX
    Explanations

    machine learning code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    流传
    -0.07
     centrif
    -0.07
    扣
    -0.07
     createContext
    -0.07
    	Return
    -0.07
    (grad
    -0.07
    غذي
    -0.06
     More
    -0.06
     stop
    -0.06
    也不是
    -0.06
    POSITIVE LOGITS
    袋
    0.08
    brands
    0.07
    ucci
    0.07
    atcher
    0.07
    سوء
    0.07
    )}}"
    0.07
    '].'"
    0.07
    esi
    0.07
     ogó
    0.07
    ='".$
    0.07
    Act Density 0.068%

    No Known Activations