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

    Neuronpedia

    INDEX
    Explanations

    Social media platforms

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    自查
    -0.07
    ᵌ
    -0.07
     расс
    -0.07
     kleine
    -0.07
    _processes
    -0.07
     userid
    -0.07
    .Surface
    -0.07
    _arguments
    -0.07
    𝑯
    -0.07
    找准
    -0.07
    POSITIVE LOGITS
     deser
    0.07
    OTA
    0.06
     Sort
    0.06
    ]'
    0.06
    }
↵
↵
    0.06
     roma
    0.06
    Sent
    0.06
     bella
    0.06
     confer
    0.06
    ملاب
    0.06
    Act Density 0.024%

    No Known Activations