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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating similarity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     einzelnen
    0.98
    いない
    0.93
    一起
    0.93
    ための
    0.92
     respectivos
    0.91
     determinados
    0.91
     jednotliv
    0.91
     vervolgens
    0.89
     respectivas
    0.86
     determinadas
    0.83
    POSITIVE LOGITS
    ities
    1.27
    ily
    1.16
     functionality
    0.98
    istically
    0.97
     sentiments
    0.95
    ार्थक
    0.95
     Yours
    0.95
     workings
    0.91
    ार्थी
    0.90
    ्तर
    0.89
    Act Density 0.086%

    No Known Activations