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

    Neuronpedia

    INDEX
    Explanations

    standard

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    azu
    -0.07
    yor
    -0.07
    _ul
    -0.07
     międzyn
    -0.07
    _TEXT
    -0.06
    加快发展
    -0.06
    -names
    -0.06
     판
    -0.06
    revision
    -0.06
     nhớ
    -0.06
    POSITIVE LOGITS
     Favor
    0.07
    特斯拉
    0.07
    岛屿
    0.07
    物资
    0.07
    ؊
    0.07
     Labor
    0.07
     -↵↵
    0.07
     filled
    0.07
     Tire
    0.07
    (REG
    0.07
    Act Density 0.005%

    No Known Activations