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

    Neuronpedia

    INDEX
    Explanations

    UI elements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _OPTION
    -0.06
     disables
    -0.06
    dispatcher
    -0.06
     sanctuary
    -0.06
    (HWND
    -0.06
    ียนบ
    -0.06
    BOOL
    -0.06
     Albany
    -0.06
    离
    -0.06
    营业
    -0.06
    POSITIVE LOGITS
    ológ
    0.07
     erroneous
    0.07
    =========↵
    0.07
    олод
    0.07
     Quaternion
    0.07
     automatically
    0.06
     follower
    0.06
     raising
    0.06
    aras
    0.06
    �
    0.06
    Act Density 0.013%

    No Known Activations