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

    Neuronpedia

    INDEX
    Explanations

    code structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <unused33>
    0.51
    odimensional
    0.51
     própri
    0.50
     принци
    0.49
    Noeud
    0.49
     pomoć
    0.49
     irmã
    0.49
     geeign
    0.49
    indx
    0.48
    ạp
    0.48
    POSITIVE LOGITS
    _
    0.45
     =
    0.41
     ​​
    0.40
     —
    0.36
     #
    0.34
     ;
    0.34
    ome
    0.34
     :
    0.33
     ::
    0.31
     :=
    0.30
    Act Density 0.224%

    No Known Activations