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

    Neuronpedia

    INDEX
    Explanations

    product type or context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     विविध
    0.51
     variously
    0.44
     seder
    0.43
     beragam
    0.43
    গুলোর
    0.41
     различи
    0.41
     pervasive
    0.40
     específicamente
    0.40
     individual
    0.40
     toBe
    0.40
    POSITIVE LOGITS
    0
    0.47
    warranty
    0.46
    當時
    0.46
     remboursement
    0.46
     कीमत
    0.46
     टाकी
    0.46
     훨
    0.46
     شركة
    0.45
     garantie
    0.45
    indungi
    0.44
    Act Density 0.001%

    No Known Activations