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

    Neuronpedia

    INDEX
    Explanations

    lesson plans/teaching blogs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Magento
    -0.08
    经销
    -0.08
    邢台
    -0.08
     نق
    -0.07
    ubishi
    -0.07
    nah
    -0.07
     القض
    -0.07
    -secret
    -0.07
    打交
    -0.07
    -registration
    -0.07
    POSITIVE LOGITS
     Quickly
    0.07
     Locked
    0.07
    一个人
    0.07
    agan
    0.06
     oppress
    0.06
     quiet
    0.06
    יד
    0.06
    ())↵↵↵
    0.06
    ACHED
    0.06
    /accounts
    0.06
    Act Density 0.047%

    No Known Activations