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

    Neuronpedia

    INDEX
    Explanations

    -

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    QL
    -0.07
     "../../../../
    -0.07
    SY
    -0.07
    ن
    -0.07
     LOAD
    -0.07
    分布在
    -0.06
    dden
    -0.06
    蚴
    -0.06
    ber
    -0.06
     그것을
    -0.06
    POSITIVE LOGITS
     Kota
    0.07
    .resume
    0.07
    Books
    0.07
     frase
    0.07
    .press
    0.07
    пуск
    0.07
    Edition
    0.07
    rees
    0.06
    传真
    0.06
     الدوري
    0.06
    Act Density 0.005%

    No Known Activations