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

    Neuronpedia

    INDEX
    Explanations

    we

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Embed
    -0.09
     ಅಧಿಕ
    -0.08
     дес
    -0.07
     వివ
    -0.07
     части
    -0.07
     тел
    -0.07
    nske
    -0.07
     rebellion
    -0.07
     EMB
    -0.07
     מב
    -0.07
    POSITIVE LOGITS
    Iteration
    0.10
     newest
    0.10
    _iteration
    0.09
     iteration
    0.09
     iterations
    0.09
    iterations
    0.09
     iter
    0.09
    iteration
    0.08
     Updating
    0.08
     Iter
    0.08
    Act Density 0.006%

    No Known Activations