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

    Neuronpedia

    INDEX
    Explanations

    dates

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     итеп
    -0.10
     alianza
    -0.09
     sowas
    -0.08
     bruke
    -0.08
    Decorator
    -0.08
     Decor
    -0.08
    ,__
    -0.08
    etti
    -0.08
    .ks
    -0.08
     victoire
    -0.08
    POSITIVE LOGITS
     பற்ற
    0.08
    ikipedia
    0.08
     imediatamente
    0.07
     purported
    0.07
     Wikipedia
    0.07
     historically
    0.07
    مط
    0.07
     검색
    0.07
    的软件
    0.07
     day's
    0.07
    Act Density 0.032%

    No Known Activations