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

    Neuronpedia

    INDEX
    Explanations

    follow

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bitk
    -0.07
    pson
    -0.06
    /sources
    -0.06
    .HandlerFunc
    -0.06
     Oyun
    -0.06
     //}↵↵
    -0.06
     Bundy
    -0.06
    pton
    -0.06
    フェ
    -0.06
     sdf
    -0.06
    POSITIVE LOGITS
     осіб
    0.07
     ping
    0.07
     कहत
    0.06
     follow
    0.06
    qq
    0.06
     companions
    0.06
     accessible
    0.06
    .*;
↵
↵
    0.06
     railroad
    0.06
     companion
    0.06
    Act Density 0.016%

    No Known Activations