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

    Neuronpedia

    INDEX
    Explanations

    distributed ledger

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    据说
    0.41
    都会
    0.38
    LookAndFeelInfo
    0.37
    ඩ්
    0.37
    otipi
    0.37
    ですし
    0.36
    ओ
    0.36
     mukaan
    0.36
    示意
    0.36
     কু
    0.36
    POSITIVE LOGITS
     fran
    0.40
     having
    0.40
    тел
    0.39
     flores
    0.39
     being
    0.39
     lign
    0.39
    ⠄
    0.39
     alum
    0.38
     fring
    0.38
     Coast
    0.38
    Act Density 0.000%

    No Known Activations