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

    Neuronpedia

    INDEX
    Explanations

    quotes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    遠
    -0.07
    Mu
    -0.07
     diagnostic
    -0.06
    ilder
    -0.06
    	cfg
    -0.06
     mysteries
    -0.06
    amı
    -0.06
    렵
    -0.06
     tac
    -0.06
    Init
    -0.06
    POSITIVE LOGITS
    ственным
    0.07
    UserController
    0.07
    latlong
    0.06
     norske
    0.06
     enhancing
    0.06
     quoi
    0.06
    GOOD
    0.06
    ευση
    0.06
     youngest
    0.06
    _ACTIONS
    0.06
    Act Density 0.044%

    No Known Activations