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

    Neuronpedia

    INDEX
    Explanations

    body measurements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ジョ
    -0.07
    _IC
    -0.07
    ưở
    -0.07
     Peters
    -0.07
    .springboot
    -0.07
     airstrikes
    -0.07
    disciplinary
    -0.07
    _e
    -0.06
     băng
    -0.06
    司马
    -0.06
    POSITIVE LOGITS
     cultures
    0.07
    欄
    0.07
     clones
    0.06
    되었
    0.06
    férence
    0.06
    ыми
    0.06
    UserInfo
    0.06
     Tokens
    0.06
    LES
    0.06
     noktas
    0.06
    Act Density 0.005%

    No Known Activations