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

    Neuronpedia

    INDEX
    Explanations

    Non-English languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    inery
    -0.06
    lookup
    -0.06
    (button
    -0.06
    alaxy
    -0.06
    _variation
    -0.06
    EDURE
    -0.06
    _difference
    -0.06
    dbname
    -0.06
    (student
    -0.06
    -variable
    -0.06
    POSITIVE LOGITS
    ﻨ
    0.07
     BaseService
    0.07
     PyQt
    0.07
    لق
    0.06
    ество
    0.06
    !“↵↵
    0.06
     бо
    0.06
     respectable
    0.06
    ?>"><
    0.06
    вол
    0.06
    Act Density 0.010%

    No Known Activations