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

    Neuronpedia

    INDEX
    Explanations

    programming variables and declaration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     โ
    0.36
     محس
    0.36
     "
    0.35
     (
    0.34
    of
    0.33
     Leng
    0.33
     ​
    0.33
     ("
    0.33
     Didier
    0.33
     टे
    0.32
    POSITIVE LOGITS
     وړاندوینه
    0.44
    ковые
    0.39
     doped
    0.39
     фаразы
    0.38
     edema
    0.38
    ᓲ
    0.38
    کات
    0.37
    ەیە
    0.37
     وړاندوینې
    0.36
     kinases
    0.36
    Act Density 0.001%

    No Known Activations