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

    Neuronpedia

    INDEX
    Explanations

    URLs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    什麼
    -0.07
     Transformation
    -0.07
     Seg
    -0.07
     benchmark
    -0.07
     ambit
    -0.06
     ABC
    -0.06
     airlines
    -0.06
    /news
    -0.06
     wee
    -0.06
    ometry
    -0.06
    POSITIVE LOGITS
    .IsTrue
    0.08
     ?>↵
    0.07
     nella
    0.07
    ﾔ
    0.07
     CLEAR
    0.07
    WRITE
    0.07
     rahatsız
    0.07
    toDouble
    0.07
    	fwrite
    0.07
    .levels
    0.07
    Act Density 0.004%

    No Known Activations