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

    Neuronpedia

    INDEX
    Explanations

    email addresses and functions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     l
    1.50
     a
    1.33
     the
    1.31
     t
    1.27
     for
    1.27
     that
    1.27
     z
    1.24
     two
    1.20
     three
    1.18
     p
    1.16
    POSITIVE LOGITS
    ik
    1.07
    don
    1.04
    HeaderAccept
    1.02
    اي
    0.99
    DON
    0.96
    isatie
    0.96
     agrícola
    0.95
    on
    0.95
    ס
    0.91
    adon
    0.90
    Act Density 1.203%

    No Known Activations