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

    Neuronpedia

    INDEX
    Explanations

    over columns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     considerato
    1.35
     clazz
    1.35
    까요
    1.29
     histórica
    1.28
     +.
    1.24
    ʺ
    1.22
    covariant
    1.21
     বিবেচিত
    1.21
     বাহাদুর
    1.20
     permut
    1.20
    POSITIVE LOGITS
     mountains
    1.05
     bounty
    1.02
    सी
    1.02
     District
    0.99
     Dallas
    0.98
    नहीं
    0.98
    iquen
    0.98
     wider
    0.98
    ircle
    0.97
    קה
    0.97
    Act Density 0.000%

    No Known Activations