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

    Neuronpedia

    INDEX
    Explanations

    blog posts, articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     }]);↵
    -0.07
     andra
    -0.06
     прав
    -0.06
     Strateg
    -0.06
    шка
    -0.06
    _Static
    -0.06
     ав
    -0.06
    msg
    -0.06
     AssemblyVersion
    -0.06
    avatars
    -0.06
    POSITIVE LOGITS
     sàng
    0.08
     considering
    0.07
    NAMESPACE
    0.07
    _',
    0.07
    ğimiz
    0.07
    ums
    0.06
    rays
    0.06
     QVBoxLayout
    0.06
     advances
    0.06
    ´t
    0.06
    Act Density 0.069%

    No Known Activations