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

    Neuronpedia

    INDEX
    Explanations

    replace

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .currentIndex
    -0.07
     angry
    -0.07
     NAS
    -0.06
     Kö
    -0.06
     warehouse
    -0.06
     warehouses
    -0.06
     Musik
    -0.06
    拥有
    -0.06
     oddly
    -0.06
    "Some
    -0.06
    POSITIVE LOGITS
    _css
    0.07
    crc
    0.07
    	kfree
    0.06
    ━�
    0.06
    gression
    0.06
     OE
    0.06
    eor
    0.06
    시오
    0.06
    etag
    0.06
     comple
    0.06
    Act Density 0.000%

    No Known Activations