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

    Neuronpedia

    INDEX
    Explanations

    provide

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     narrator
    -0.08
     diğer
    -0.08
    ）（
    -0.07
     overpower
    -0.07
    在那里
    -0.07
     enim
    -0.07
     nick
    -0.07
     wie
    -0.07
    /or
    -0.07
    如
    -0.07
    POSITIVE LOGITS
     Listing
    0.09
     Recommendations
    0.08
     הם
    0.08
     Informationen
    0.08
    Listing
    0.08
     도움이
    0.08
     Generate
    0.08
     سياسة
    0.08
     제가
    0.08
     Answers
    0.08
    Act Density 0.016%

    No Known Activations