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

    Neuronpedia

    INDEX
    Explanations

    premieres and debuts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Alger
    -0.07
    student
    -0.07
    .getTable
    -0.07
     joke
    -0.07
    莱
    -0.07
     shm
    -0.07
     vide
    -0.07
    工业大学
    -0.07
     wage
    -0.06
     bomb
    -0.06
    POSITIVE LOGITS
    勾
    0.08
    رام
    0.08
    ット
    0.07
    らず
    0.07
     premiered
    0.07
    tower
    0.07
    irá
    0.07
    ESTAMP
    0.06
    تواصل
    0.06
     vòng
    0.06
    Act Density 0.048%

    No Known Activations