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

    Neuronpedia

    INDEX
    Explanations

    Code delimiters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    aturday
    -0.07
     Employer
    -0.06
    \Facades
    -0.06
     dağı
    -0.06
    /menu
    -0.06
    _TESTS
    -0.06
     Fishing
    -0.06
     arrangements
    -0.06
    _format
    -0.06
     выступ
    -0.06
    POSITIVE LOGITS
    詳細
    0.07
    .LatLng
    0.07
    (TokenType
    0.06
    tags
    0.06
    娜
    0.06
     replicate
    0.06
     completeness
    0.06
    (W
    0.06
    ไฟล
    0.06
     В
    0.06
    Act Density 0.016%

    No Known Activations