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

    Neuronpedia

    INDEX
    Explanations

    LTS, prospects, :=

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ﻤ
    1.40
     imprisonment
    1.27
    Պ
    1.26
    thed
    1.23
     redefining
    1.22
    kelijk
    1.21
    چال
    1.20
    Ֆ
    1.18
     facie
    1.18
    opolitical
    1.18
    POSITIVE LOGITS
    е
    1.19
    て
    1.11
    ه
    1.11
    т
    1.10
    на
    1.08
     punt
    1.07
    сь
    1.07
    не
    1.05
    े
    1.03
    ดี
    1.02
    Act Density 0.001%

    No Known Activations