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

    Neuronpedia

    INDEX
    Explanations

    Names/Usernames

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    typed
    -0.08
     kart
    -0.07
    鳒
    -0.07
     Cowboy
    -0.06
    ENTER
    -0.06
    clair
    -0.06
    []=$
    -0.06
    区
    -0.06
    梭
    -0.06
     THINK
    -0.06
    POSITIVE LOGITS
    ):-
    0.07
     -.
    0.07
    Reaction
    0.07
     irc
    0.07
     criticized
    0.07
     وقد
    0.07
    	Description
    0.07
     pudo
    0.07
    OnError
    0.07
    ﺣ
    0.07
    Act Density 0.395%

    No Known Activations