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

    Neuronpedia

    INDEX
    Explanations

    to the extent

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     તો
    0.85
    ትን
    0.84
    lectricité
    0.81
     Результа
    0.81
    ቸውን
    0.80
     pptd
    0.80
    ቱን
    0.80
     darn
    0.79
     iphdr
    0.78
     रकम
    0.76
    POSITIVE LOGITS
     fullest
    1.14
     liking
    1.14
     detriment
    1.08
     extent
    1.06
    extent
    1.02
     juncture
    0.90
     deserving
    0.88
     resemble
    0.87
     chagrin
    0.86
     redor
    0.85
    Act Density 0.126%

    No Known Activations