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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rok
    -0.08
     refer
    -0.07
    eec
    -0.07
     discuss
    -0.07
    北
    -0.06
    leyen
    -0.06
     이제
    -0.06
     genome
    -0.06
     이어
    -0.06
     analysis
    -0.06
    POSITIVE LOGITS
    ุท
    0.06
     생산
    0.06
     Mitsubishi
    0.06
     tinder
    0.06
    <context
    0.06
     *_
    0.06
    _export
    0.06
    ()})↵
    0.06
     пищ
    0.06
     hiển
    0.06
    Act Density 0.053%

    No Known Activations