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

    Neuronpedia

    INDEX
    Explanations

    technical processes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    高
    -0.07
    영상
    -0.07
    混合
    -0.06
     креп
    -0.06
    丁
    -0.06
     infrared
    -0.06
     高
    -0.06
    -Out
    -0.06
    説明
    -0.06
    約
    -0.06
    POSITIVE LOGITS
    (sl
    0.07
    ujte
    0.07
    este
    0.06
    |:
    0.06
     aliqu
    0.06
    ivet
    0.06
    報
    0.06
     taught
    0.06
    elleicht
    0.06
     backstage
    0.06
    Act Density 0.208%

    No Known Activations