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

    Neuronpedia

    INDEX
    Explanations

    awareness

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     التابعة
    -0.08
    ဆို
    -0.08
     eut
    -0.08
    ithe
    -0.08
     showcases
    -0.08
    ometer
    -0.07
     skon
    -0.07
    usable
    -0.07
    .bad
    -0.07
    agini
    -0.07
    POSITIVE LOGITS
    事项
    0.17
    事項
    0.15
    사항
    0.14
     beachten
    0.13
     precautions
    0.13
     사항
    0.13
    注意
    0.12
    牢记
    0.12
     கவ
    0.12
     ધ્યાન
    0.11
    Act Density 0.075%

    No Known Activations