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

    Neuronpedia

    INDEX
    Explanations

    composed of scientific subjects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     protes
    0.42
     voraus
    0.36
     evanescent
    0.35
    ഹി
    0.35
     vuccanti
    0.35
     ആക
    0.34
     벗
    0.34
     不能
    0.34
     poker
    0.34
    ﻊ
    0.34
    POSITIVE LOGITS
    Fancy
    0.43
    alic
    0.41
     başarılı
    0.40
     ut
    0.40
    itor
    0.40
    ast
    0.39
     UT
    0.39
     kult
    0.39
    ut
    0.39
     ASK
    0.38
    Act Density 0.005%

    No Known Activations