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

    Neuronpedia

    INDEX
    Explanations

    in summary or short

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     &'
    0.30
    ℙ
    0.29
     Kräfte
    0.29
    Fee
    0.28
    াহিয়ার
    0.28
     आउटफिट
    0.27
     Approximate
    0.27
    MING
    0.27
    Usuario
    0.26
     IndexError
    0.26
    POSITIVE LOGITS
    clud
    0.43
     welchem
    0.41
     a
    0.40
     caso
    0.40
     nutshell
    0.39
    spirational
    0.38
     cazul
    0.38
     котором
    0.37
    clusively
    0.37
     which
    0.36
    Act Density 0.160%

    No Known Activations