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

    Neuronpedia

    INDEX
    Explanations

    consult with a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Emails
    0.71
    ysł
    0.65
     값이
    0.64
    Using
    0.63
    Transactions
    0.62
     Интере
    0.59
    צי
    0.59
    Còn
    0.59
    च्युअल
    0.58
    מים
    0.58
    POSITIVE LOGITS
     the
    1.16
     a
    0.96
     our
    0.91
     either
    0.90
     their
    0.89
     into
    0.85
     this
    0.85
     these
    0.84
     up
    0.80
     an
    0.79
    Act Density 0.166%

    No Known Activations