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

    Neuronpedia

    INDEX
    Explanations

    }

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    停留在
    -0.08
    Feedback
    -0.08
    所以在
    -0.07
     consuming
    -0.07
     miền
    -0.07
     interact
    -0.07
    岽
    -0.07
    秉承
    -0.07
    녹
    -0.07
    셉
    -0.07
    POSITIVE LOGITS
    alias
    0.08
    _prefs
    0.07
    ).
    0.07
     MAK
    0.07
    |\
    0.07
    .Comparator
    0.07
     ero
    0.07
    (|
    0.07
     }↵
    0.07
    [obj
    0.06
    Act Density 0.087%

    No Known Activations