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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     propor
    -0.08
     parentes
    -0.08
     magnitude
    -0.08
    iter
    -0.08
    ènes
    -0.08
     extrusion
    -0.08
    éin
    -0.07
    Magnitude
    -0.07
     已
    -0.07
     Pand
    -0.07
    POSITIVE LOGITS
     demeanor
    0.09
     طويلة
    0.08
     melancholy
    0.08
     silence
    0.08
     tiba
    0.08
     ക്ഷ
    0.08
     silêncio
    0.08
     largos
    0.08
    Consume
    0.07
     ശേഷം
    0.07
    Act Density 0.013%

    No Known Activations