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

    Neuronpedia

    INDEX
    Explanations

    conditional questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     делать
    0.45
     harán
    0.44
     válido
    0.44
     hacerlo
    0.43
     haremos
    0.43
    ത്തുന്ന
    0.41
     yapacağız
    0.40
     wundersch
    0.40
    넣
    0.39
     válida
    0.39
    POSITIVE LOGITS
     Maybe
    0.51
     Nevertheless
    0.51
     kanske
    0.49
     maybe
    0.46
     Perhaps
    0.45
     tipo
    0.41
     However
    0.41
     nevertheless
    0.40
     perhaps
    0.40
    maybe
    0.39
    Act Density 0.023%

    No Known Activations