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

    Neuronpedia

    INDEX
    Explanations

    Area

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _hook
    -0.06
    WhatsApp
    -0.06
     mocking
    -0.06
    、新
    -0.06
     Winston
    -0.06
    .prototype
    -0.06
     повинен
    -0.06
    prepend
    -0.06
     độc
    -0.06
    皇
    -0.06
    POSITIVE LOGITS
     area
    0.20
     Area
    0.19
    Area
    0.16
     areas
    0.15
     Areas
    0.14
     AREA
    0.13
    area
    0.13
    -area
    0.11
    areas
    0.10
     área
    0.10
    Act Density 0.038%

    No Known Activations