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

    Neuronpedia

    INDEX
    Explanations

    FORE

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     exploited
    -0.07
    index
    -0.07
    dist
    -0.07
    ForResult
    -0.07
    人才培养
    -0.07
    捐款
    -0.07
     היתר
    -0.07
    /↵↵↵↵
    -0.07
    之夜
    -0.07
    科技股份
    -0.07
    POSITIVE LOGITS
    <small
    0.07
     sandy
    0.07
    抖
    0.07
    .ExecuteScalar
    0.07
     Cookbook
    0.07
    ₒ
    0.06
    .BASE
    0.06
    甩
    0.06
    �
    0.06
    흘
    0.06
    Act Density 0.003%

    No Known Activations