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

    Neuronpedia

    INDEX
    Explanations

    javascript require document

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     scon
    0.39
     всіх
    0.39
     وار
    0.38
     Enseñanza
    0.38
    ++]
    0.38
     intorno
    0.38
     varía
    0.37
    $)$.
    0.37
     вари
    0.37
     ಬಂದ
    0.37
    POSITIVE LOGITS
     require
    0.84
    require
    0.75
     (()
    0.68
     new
    0.65
     jest
    0.60
     document
    0.59
     ()
    0.59
    (()
    0.58
     requires
    0.57
    new
    0.55
    Act Density 0.006%

    No Known Activations