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

    Neuronpedia

    INDEX
    Explanations

    JSON schema `$ref`, `$schema`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ﻙ
    1.14
    𝗔
    1.09
    د
    1.05
    𝙈
    1.01
    henderit
    1.00
    ኚ
    1.00
    できる
    0.99
    ości
    0.96
     দ্য
    0.96
     luciferase
    0.95
    POSITIVE LOGITS
    $
    1.08
    .
    1.00
    %
    1.00
     pertandingan
    0.98
    ava
    0.97
     Bolsa
    0.96
    includes
    0.94
    6
    0.94
    ্লাহ
    0.93
    icht
    0.91
    Act Density 0.003%

    No Known Activations