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

    Neuronpedia

    INDEX
    Explanations

    solving mathematical equations for x

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ۋە
    1.13
    savvy
    1.10
    및
    1.06
    ﺎ
    1.01
    ﻮ
    0.99
    ɪ
    0.96
     iniziale
    0.95
    𝐚
    0.93
     употре
    0.92
     metu
    0.92
    POSITIVE LOGITS
    ق
    0.88
     $\
    0.82
    ↵↵
    0.77
     Resource
    0.74
    Proceedings
    0.73
    ので
    0.72
     Hiroshima
    0.70
     Engagement
    0.69
     Atlas
    0.69
     Enrichment
    0.69
    Act Density 0.193%

    No Known Activations