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

    Neuronpedia

    INDEX
    Explanations

    education

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    AIN
    -0.06
     xảy
    -0.06
    -М
    -0.06
    ))
↵
    -0.06
    絶
    -0.06
    _queue
    -0.05
    ToEnd
    -0.05
    QUE
    -0.05
     erkek
    -0.05
    喊
    -0.05
    POSITIVE LOGITS
    vertical
    0.07
    apper
    0.07
     teacher
    0.07
     kaynağı
    0.07
    盒
    0.06
    .spacing
    0.06
     Grad
    0.06
    σταση
    0.06
     Mild
    0.06
    .firstName
    0.06
    Act Density 0.023%

    No Known Activations