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

    Neuronpedia

    INDEX
    Explanations

    feet

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     DataManager
    -0.08
    M
    -0.08
    ’.↵↵
    -0.07
    フ�
    -0.07
    [T
    -0.07
     prise
    -0.07
    (bodyParser
    -0.07
    涩
    -0.07
    燥
    -0.07
    这首
    -0.07
    POSITIVE LOGITS
     Constitution
    0.07
    incorrect
    0.07
    .BorderColor
    0.07
    คอนโด
    0.07
    Ғ
    0.07
     segregation
    0.06
     parentheses
    0.06
    𝓻
    0.06
    杆
    0.06
     TokenType
    0.06
    Act Density 0.008%

    No Known Activations