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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     VH
    -0.08
    %).↵↵
    -0.07
    خرج
    -0.07
    	dp
    -0.07
     ..."↵↵
    -0.07
    """↵↵
    -0.07
     pressure
    -0.07
    ↵        
↵
    -0.07
     "")↵↵
    -0.07
     tienes
    -0.07
    POSITIVE LOGITS
    .mousePosition
    0.07
    общ
    0.07
    anth
    0.07
    -conscious
    0.07
    め
    0.07
    -best
    0.06
    localized
    0.06
    ünün
    0.06
    -most
    0.06
    웛
    0.06
    Act Density 0.088%

    No Known Activations