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

    Neuronpedia

    INDEX
    Explanations

    subject/topic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     تضيفلها
    -1.26
    findpost
    -1.21
     חיצוניים
    -1.13
    Personensuche
    -1.12
    脚注の使い方
    -1.09
     NSCoder
    -1.06
     propOrder
    -1.06
    ConstraintMaker
    -1.05
     myſelf
    -1.05
     AssemblyCulture
    -1.05
    POSITIVE LOGITS
    -
    0.67
    (
    0.66
    ,
    0.56
     and
    0.53
     for
    0.52
    '
    0.52
     
    0.50
    .
    0.49
    /
    0.48
     so
    0.46
    Act Density 0.031%

    No Known Activations