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

    Neuronpedia

    INDEX
    Explanations

    late today or solo

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ת
    1.12
    лександ
    1.10
    ραι
    1.08
    к
    1.08
    oes
    1.06
    ة
    1.06
    ю
    1.05
    లోకి
    1.05
     reputation
    1.04
    л
    1.03
    POSITIVE LOGITS
     awhile
    1.00
     chromatin
    0.98
     निव
    0.98
    ﺶ
    0.95
     ဒီ
    0.94
    $\$
    0.93
     sınav
    0.93
     resumen
    0.93
    ﻔ
    0.90
    ၂
    0.86
    Act Density 0.001%

    No Known Activations