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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     GNOME
    -0.08
    帶
    -0.07
    pNet
    -0.07
    TreeWidgetItem
    -0.07
    .currentIndex
    -0.06
    週
    -0.06
     striped
    -0.06
     enumerable
    -0.06
    Responsive
    -0.06
     migrate
    -0.06
    POSITIVE LOGITS
    ‌ها
    0.07
    READ
    0.06
    ll
    0.06
    "name
    0.06
     */↵↵↵↵
    0.06
    acc
    0.06
     apartheid
    0.06
     authentic
    0.06
    ngo
    0.06
     *)(
    0.06
    Act Density 0.021%

    No Known Activations