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

    Neuronpedia

    INDEX
    Explanations

    car parts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dönem
    -0.07
     separ
    -0.07
    application
    -0.07
     пояс
    -0.07
    usters
    -0.07
    active
    -0.07
    Gate
    -0.07
     clums
    -0.06
     gratitude
    -0.06
     Growing
    -0.06
    POSITIVE LOGITS
    _KeyPress
    0.06
    ;&#
    0.06
     ارتف
    0.06
    ceased
    0.06
    .PORT
    0.05
    SessionFactory
    0.05
                                 ↵
    0.05
    .word
    0.05
    ٩
    0.05
                                   ↵
    0.05
    Act Density 0.038%

    No Known Activations