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

    Neuronpedia

    INDEX
    Explanations

    predicting the next word

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Episodes
    0.44
     esperaba
    0.43
     classifiers
    0.41
     clasific
    0.38
     homeomorphic
    0.38
     ایکسپریس
    0.38
     الحب
    0.38
    길
    0.38
     instância
    0.38
    毀
    0.38
    POSITIVE LOGITS
     next
    0.68
    下一个
    0.66
     अगला
    0.64
     words
    0.63
     Next
    0.63
     nächste
    0.61
     próxima
    0.60
     prochaine
    0.58
     próximas
    0.58
    次の
    0.57
    Act Density 0.027%

    No Known Activations