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

    Neuronpedia

    INDEX
    Explanations

    argv

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     المش
    -0.07
     dny
    -0.07
    _sent
    -0.07
    _Interface
    -0.07
    _INC
    -0.07
    Mal
    -0.07
    transparent
    -0.07
    metis
    -0.06
     Haus
    -0.06
     Crescent
    -0.06
    POSITIVE LOGITS
    489
    0.07
     millennia
    0.06
     ivory
    0.06
    TV
    0.06
    ew
    0.06
     ]↵↵
    0.06
     Bangalore
    0.06
     Dominion
    0.06
     뉴
    0.06
     celebrities
    0.06
    Act Density 0.002%

    No Known Activations