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

    Neuronpedia

    INDEX
    Explanations

    parentheses

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Jen
    -0.07
    .GetObject
    -0.07
    桑
    -0.06
     Playground
    -0.06
     people
    -0.06
    .ย
    -0.06
    Establish
    -0.06
     Force
    -0.06
     loung
    -0.06
    ,LOCATION
    -0.06
    POSITIVE LOGITS
     fruity
    0.07
     domu
    0.07
    'aff
    0.06
     گیری
    0.06
    ■■
    0.06
    ่
    0.06
    _"
    0.06
    通過
    0.06
    国際
    0.06
    irse
    0.06
    Act Density 0.056%

    No Known Activations