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

    Neuronpedia

    INDEX
    Explanations

    cosmetic surgery

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     participants
    -0.07
    pwd
    -0.07
    ARIO
    -0.07
    AVED
    -0.06
     languages
    -0.06
     privile
    -0.06
    ække
    -0.06
    avig
    -0.06
     Anal
    -0.06
    trans
    -0.06
    POSITIVE LOGITS
    941
    0.07
     knob
    0.07
     тепло
    0.06
    -border
    0.06
    WithName
    0.06
     канди
    0.06
    aque
    0.06
    isOpen
    0.06
    .emplace
    0.06
    [indexPath
    0.06
    Act Density 0.015%

    No Known Activations