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

    Neuronpedia

    INDEX
    Explanations

    lists of items and instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ani
    0.41
    Int
    0.41
    giveness
    0.41
    Ind
    0.41
     Environmental
    0.40
    Environmental
    0.40
    ui
    0.40
    az
    0.39
    ânt
    0.39
    na
    0.38
    POSITIVE LOGITS
     hardcore
    0.50
     classed
    0.48
     maatau
    0.45
    सीआर
    0.44
     ALLOYS
    0.44
     लोकांना
    0.44
    鐵
    0.43
    ធម្ម
    0.43
    ﻌ
    0.42
     आहेत
    0.41
    Act Density 0.001%

    No Known Activations