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

    Neuronpedia

    INDEX
    Explanations

    tips and instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    되어
    -0.08
     tersebut
    -0.08
    ???↵↵
    -0.08
     müs
    -0.08
    这一
    -0.07
     persons
    -0.07
    crito
    -0.07
     oldukça
    -0.07
     framework
    -0.07
    Val
    -0.07
    POSITIVE LOGITS
    不要
    0.13
     ہمیشہ
    0.12
     помнить
    0.12
    勿
    0.12
     избег
    0.12
     соблюдать
    0.11
    牢记
    0.11
     תמיד
    0.11
     внимательно
    0.11
     cherish
    0.11
    Act Density 0.091%

    No Known Activations