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

    Neuronpedia

    INDEX
    Explanations

    special markers or code comments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ዐ
    0.40
    лена
    0.39
     reliance
    0.38
    reliance
    0.36
     cul
    0.36
    ведения
    0.36
     vig
    0.35
    ما
    0.34
    விட
    0.34
     باغ
    0.34
    POSITIVE LOGITS
     randomize
    0.43
     Taal
    0.43
     toc
    0.42
     Toc
    0.42
     ~(~)
    0.41
     ListNode
    0.41
    oua
    0.38
     Skin
    0.38
     SimSun
    0.38
     AST
    0.38
    Act Density 0.000%

    No Known Activations