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

    Neuronpedia

    INDEX
    Explanations

    components and hardware

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Utt
    -0.08
     отпуск
    -0.08
     врачу
    -0.07
     предложение
    -0.07
     suppressant
    -0.07
     выполня
    -0.07
    (Path
    -0.07
    섭
    -0.07
     дед
    -0.07
     usaha
    -0.07
    POSITIVE LOGITS
    electronics
    0.10
    embedded
    0.10
     نصب
    0.09
     electronics
    0.09
    mechan
    0.08
    ocabulary
    0.08
    tiny
    0.08
     composants
    0.08
    addies
    0.08
    installed
    0.08
    Act Density 0.084%

    No Known Activations