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

    Neuronpedia

    INDEX
    Explanations

    defining categories or states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    សម្រ
    0.45
     ಮುಂದ
    0.43
     appunto
    0.43
    ol
    0.43
     പ്രത്യേക
    0.43
    0.43
    గానే
    0.42
    aparikkh
    0.42
    is
    0.41
    तरह
    0.41
    POSITIVE LOGITS
    ،
    0.71
    ，
    0.63
    (
    0.55
    5
    0.55
    、
    0.54
    （
    0.54
    6
    0.54
    9
    0.51
    =
    0.50
     (
    0.50
    Act Density 0.154%

    No Known Activations