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

    Neuronpedia

    INDEX
    Explanations

    German text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    イト
    -0.07
    рит
    -0.06
    游
    -0.06
     ghế
    -0.06
    _pr
    -0.06
    	dd
    -0.06
    imps
    -0.06
    lrt
    -0.06
     наз
    -0.06
     chosen
    -0.06
    POSITIVE LOGITS
    ),"
    0.07
    례
    0.07
    .Optional
    0.07
     Pixel
    0.07
     commemor
    0.07
     신규
    0.07
     domic
    0.06
    ."<
    0.06
    .peek
    0.06
    ừa
    0.06
    Act Density 0.047%

    No Known Activations