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

    Neuronpedia

    INDEX
    Explanations

    Star Wars episodes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    BAC
    -0.07
     multifunction
    -0.07
     Jungle
    -0.07
     espanhol
    -0.07
     coloured
    -0.07
     agradável
    -0.07
    etu
    -0.07
    _GRE
    -0.07
    ential
    -0.07
     Amazon
    -0.07
    POSITIVE LOGITS
    .Render
    0.09
    (render
    0.09
    (Render
    0.09
    .subtitle
    0.08
    /render
    0.08
     Staat
    0.08
     trilogy
    0.08
     قى
    0.08
     ಪ್ರಕ
    0.08
     Subtitle
    0.08
    Act Density 0.004%

    No Known Activations