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

    Neuronpedia

    INDEX
    Explanations

    ial

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    mind
    -0.07
    disabled
    -0.07
    лених
    -0.06
    Labour
    -0.06
     Audi
    -0.06
    Car
    -0.06
     Subway
    -0.06
    ()?.
    -0.06
    Colour
    -0.06
     spinning
    -0.06
    POSITIVE LOGITS
    ẫ
    0.07
    _repeat
    0.07
     політики
    0.07
     мере
    0.06
    öh
    0.06
    .xtext
    0.06
     يجب
    0.06
    .TrimSpace
    0.06
     '{"
    0.06
     twitter
    0.06
    Act Density 0.211%

    No Known Activations