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

    Neuronpedia

    INDEX
    Explanations

    special characters and code markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vest
    0.43
     définit
    0.42
    Genetic
    0.42
     subsidy
    0.41
     সফর
    0.40
    ﻯ
    0.40
    Assemble
    0.40
    に対応
    0.39
    二氧化
    0.38
    Спољашње
    0.38
    POSITIVE LOGITS
    кур
    0.41
    aders
    0.40
    હેરા
    0.40
    బ్బ
    0.38
     фигуры
    0.37
    arrow
    0.36
     в
    0.36
     Arrows
    0.36
    arithmic
    0.36
     <-
    0.36
    Act Density 0.000%

    No Known Activations