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

    Neuronpedia

    INDEX
    Explanations

    financial terms

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    н
    0.67
     cậu
    0.64
    スー
    0.63
    0.63
    但他
    0.62
    ぃ
    0.62
     müs
    0.61
     dined
    0.59
    न
    0.59
    น
    0.59
    POSITIVE LOGITS
    VAT
    0.70
     majorité
    0.63
    ECM
    0.63
     সকালে
    0.62
    span
    0.62
    FOR
    0.61
     পথে
    0.60
    path
    0.60
    conform
    0.58
     পথ
    0.58
    Act Density 0.000%

    No Known Activations