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

    Neuronpedia

    INDEX
    Explanations

    articles before nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    2
    1.64
    3
    1.51
    4
    1.50
    াল
    1.46
    8
    1.45
    是
    1.43
    7
    1.43
    9
    1.38
    5
    1.36
    In
    1.33
    POSITIVE LOGITS
     momento
    1.36
     próprio
    1.29
    /"><
    1.21
     fazer
    1.14
    〔
    1.11
    histogram
    1.08
     més
    1.08
     tempo
    1.07
     propio
    1.06
     nº
    1.06
    Act Density 0.164%

    No Known Activations