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

    Neuronpedia

    INDEX
    Explanations

    pip install

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ೋಜನ
    0.43
    ÍA
    0.39
    เปิด
    0.39
    锶
    0.37
    粞
    0.37
    ведение
    0.36
    栻
    0.36
    ⵛ
    0.36
    ющим
    0.36
    ıdır
    0.36
    POSITIVE LOGITS
     install
    1.08
    install
    1.02
    Install
    1.01
     Install
    1.00
     installs
    0.95
     installing
    0.90
    Installing
    0.85
    安装
    0.83
     instal
    0.82
     Installing
    0.82
    Act Density 0.024%

    No Known Activations