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

    Neuronpedia

    INDEX
    Explanations

    uv

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (div
    -0.08
     expelled
    -0.08
     reads
    -0.07
    	rc
    -0.07
    찬
    -0.07
    城墙
    -0.07
     boilers
    -0.07
     severed
    -0.07
    炷
    -0.07
    .getDeclared
    -0.07
    POSITIVE LOGITS
    增多
    0.07
    �
    0.07
    ATO
    0.06
    上年
    0.06
    mkdir
    0.06
     statute
    0.06
    ATA
    0.06
     ứng
    0.06
    OMETRY
    0.06
     fung
    0.06
    Act Density 0.007%

    No Known Activations