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

    Neuronpedia

    INDEX
    Explanations

    open

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _window
    -0.06
    Marshal
    -0.06
     Saturn
    -0.06
    addColumn
    -0.06
    Machine
    -0.06
     keyCode
    -0.06
     싱
    -0.06
     distribute
    -0.06
    �
    -0.06
     bozuk
    -0.06
    POSITIVE LOGITS
    úde
    0.07
     nghĩ
    0.06
    ilities
    0.06
    aper
    0.06
     Yoga
    0.06
    ampionship
    0.06
    ！”↵↵
    0.06
    光
    0.06
    Ｍ
    0.06
     мис
    0.06
    Act Density 0.001%

    No Known Activations