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

    Neuronpedia

    INDEX
    Explanations

    Adverbs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     présidentielle
    -0.79
    Personensuche
    -0.75
     brilliantly
    -0.74
     culturelle
    -0.69
     oddly
    -0.68
     chaude
    -0.68
     weirdly
    -0.68
     Theſe
    -0.66
    worldly
    -0.66
     Wikimedijinoj
    -0.65
    POSITIVE LOGITS
     NSCoder
    0.62
     selected
    0.50
     BoxDecoration
    0.50
    SequentialGroup
    0.49
    Activités
    0.49
     accurate
    0.45
     désolés
    0.45
     transferred
    0.45
    InitStruct
    0.45
     fixed
    0.44
    Act Density 0.105%

    No Known Activations