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

    Neuronpedia

    INDEX
    Explanations

    Code and numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ADS
    -0.06
     Saint
    -0.06
     Trash
    -0.06
    vw
    -0.06
     UNIVERS
    -0.06
     stubborn
    -0.06
     zat
    -0.06
     Setter
    -0.06
     View
    -0.06
     '<?
    -0.06
    POSITIVE LOGITS
    いい
    0.07
    imdi
    0.07
    Segment
    0.06
    .stringValue
    0.06
    阅读次数
    0.06
     Meer
    0.06
     주요
    0.06
     resmi
    0.06
    ασία
    0.06
    (bodyParser
    0.06
    Act Density 0.001%

    No Known Activations