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

    Neuronpedia

    INDEX
    Explanations

    notably specific facts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    vang
    1.31
    很多的
    1.29
     সমস্ত
    1.25
    rea
    1.22
     etc
    1.20
     সকল
    1.20
     ২০১১
    1.19
     revolved
    1.18
     impart
    1.16
     lc
    1.13
    POSITIVE LOGITS
     wry
    1.28
    форд
    1.26
    :
    1.13
     ferrugine
    1.11
    Notably
    1.08
     smug
    1.06
     olsa
    1.06
     discernible
    1.05
    悱
    1.05
     nettement
    1.05
    Act Density 0.001%

    No Known Activations