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

    Neuronpedia

    INDEX
    Explanations

    fundamentally subjective reality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    нцикло
    0.39
    voy
    0.38
    Dictionary
    0.38
    Leer
    0.37
     Desk
    0.37
    iddy
    0.37
    Din
    0.37
     DIN
    0.36
    Random
    0.36
    Mon
    0.36
    POSITIVE LOGITS
    ACCEPT
    0.41
    ﻷ
    0.39
    焔
    0.39
    ILITIES
    0.38
     LOCKED
    0.37
    氈
    0.37
     subl
    0.37
    GLIGENCE
    0.36
    лябин
    0.36
    ಿತ್ತು
    0.36
    Act Density 0.000%

    No Known Activations