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

    Neuronpedia

    INDEX
    Explanations

    stronger

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Typically
    -0.06
    Mode
    -0.06
     anom
    -0.06
    features
    -0.06
    652
    -0.06
    ничес
    -0.06
    	public
    -0.06
    ationally
    -0.06
    628
    -0.06
    Turkey
    -0.06
    POSITIVE LOGITS
     iOS
    0.07
    apr
    0.07
    ::_('
    0.06
    graphics
    0.06
    .SelectedValue
    0.06
    اث
    0.06
     weaker
    0.06
     Interested
    0.06
    家
    0.06
     VStack
    0.06
    Act Density 0.016%

    No Known Activations