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

    Neuronpedia

    INDEX
    Explanations

    Explanation:

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    될
    0.46
    뀔
    0.45
     좋을
    0.43
    かれる
    0.41
     வழங்கப்படும்
    0.40
    原子炉
    0.40
    거운
    0.40
     probablemente
    0.39
    ):=
    0.38
    为其
    0.38
    POSITIVE LOGITS
     हमने
    0.56
     acima
    0.56
     tutaj
    0.54
     powy
    0.54
     abbiamo
    0.53
     above
    0.52
     nossa
    0.52
    notice
    0.51
     nosso
    0.50
     oben
    0.50
    Act Density 0.171%

    No Known Activations