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

    Neuronpedia

    INDEX
    Explanations

    Britannica topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    쐞
    0.43
    वणे
    0.42
     платформа
    0.40
    habalar
    0.40
    বন্ধন
    0.40
     savk
    0.39
     savons
    0.39
     intérieure
    0.39
     digitale
    0.39
     स्ट्रीमिंग
    0.38
    POSITIVE LOGITS
     famed
    0.42
     renowned
    0.40
     gardens
    0.39
     notorious
    0.37
     termin
    0.37
     descu
    0.37
     rumored
    0.36
    Ї
    0.36
     four
    0.36
    \)
    0.36
    Act Density 0.001%

    No Known Activations