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

    Neuronpedia

    INDEX
    Explanations

    Speed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rico
    -0.08
     اص
    -0.07
     será
    -0.06
    遠
    -0.06
    ーチ
    -0.06
     seu
    -0.06
     viên
    -0.06
    eec
    -0.06
    itou
    -0.06
     हज
    -0.06
    POSITIVE LOGITS
    ritable
    0.07
    agnostic
    0.07
    Capability
    0.07
     digits
    0.06
    .inverse
    0.06
     характеристики
    0.06
    abeth
    0.06
     用
    0.06
     Hobby
    0.06
    registration
    0.06
    Act Density 0.000%

    No Known Activations