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

    Neuronpedia

    INDEX
    Explanations

    file

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     minX
    -0.07
    	describe
    -0.07
     apocalypse
    -0.07
     thầy
    -0.07
     estud
    -0.07
     potrà
    -0.07
    ثقافة
    -0.07
    .prof
    -0.06
    ừng
    -0.06
     sociedad
    -0.06
    POSITIVE LOGITS
     NBA
    0.08
    -fill
    0.07
     Hot
    0.07
     Ea
    0.07
    北京赛车
    0.07
    bob
    0.07
    (QL
    0.06
     blouse
    0.06
    FTWARE
    0.06
     favorable
    0.06
    Act Density 0.000%

    No Known Activations