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

    Neuronpedia

    INDEX
    Explanations

    I can

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     можно
    0.70
     можна
    0.65
     Можно
    0.58
     można
    0.58
     можем
    0.55
    也可
    0.54
     podremos
    0.52
    是可以
    0.52
    Можно
    0.52
    можно
    0.50
    POSITIVE LOGITS
     Accurate
    0.44
     bei
    0.41
     Accuracy
    0.39
     storytelling
    0.39
     grace
    0.38
    त्रे
    0.38
     Ge
    0.38
     minute
    0.37
     Fixed
    0.37
     Manage
    0.37
    Act Density 0.002%

    No Known Activations