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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Paste
    -0.07
    僕
    -0.07
     Cummings
    -0.06
    く
    -0.06
    **↵
    -0.06
    (layers
    -0.06
    useState
    -0.06
    ม
    -0.06
    UserProfile
    -0.06
    //-----------------------------------------------------------------------------↵
    -0.06
    POSITIVE LOGITS
    尾
    0.07
     ناب
    0.07
     Durham
    0.06
    	screen
    0.06
    SCRIPT
    0.06
    inions
    0.06
     Labels
    0.06
    (SS
    0.06
    516
    0.06
     reel
    0.06
    Act Density 0.057%

    No Known Activations