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

    Neuronpedia

    INDEX
    Explanations

    writing and generating code or text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Tit
    1.11
    ﻤ
    1.10
    en
    1.08
    T
    1.06
    minus
    1.05
    से
    1.03
    Journey
    0.99
    K
    0.99
    יו
    0.98
    Cyt
    0.97
    POSITIVE LOGITS
     hiểu
    1.25
     sàng
    1.20
    ную
    1.15
    emics
    1.14
    ivät
    1.11
     defaultdict
    1.11
    inhas
    1.11
    टीना
    1.11
    ="__
    1.10
     Sumatra
    1.09
    Act Density 0.000%

    No Known Activations