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

    Neuronpedia

    INDEX
    Explanations

    Radix, empirics, inequalities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    鸶
    -3.16
    ו
    -3.02
    an
    -3.00
    in
    -2.89
    n
    -2.89
    al
    -2.86
     itſelf
    -2.83
    胧
    -2.81
    as
    -2.73
     艺术
    -2.64
    POSITIVE LOGITS
     
    3.09
     i
    2.95
    1
    2.91
     zweite
    2.88
     .
    2.72
    /
    2.72
     e
    2.55
     o
    2.42
     komplette
    2.42
     &
    2.41
    Act Density 1.232%

    No Known Activations