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

    Neuronpedia

    INDEX
    Explanations

    problem

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     manufacturers
    -0.09
     Jurassic
    -0.09
     grams
    -0.08
    吨
    -0.08
     pot
    -0.08
    Din
    -0.08
    Rapid
    -0.07
     manufacturer
    -0.07
     Rapid
    -0.07
    は禁止
    -0.07
    POSITIVE LOGITS
     Retry
    0.09
     разобраться
    0.09
     рас
    0.08
     losse
    0.08
    人生
    0.08
     улучш
    0.08
     jot
    0.08
     gently
    0.08
     calmly
    0.08
     Нав
    0.08
    Act Density 0.066%

    No Known Activations