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

    Neuronpedia

    INDEX
    Explanations

    IDE and software tools

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     processes
    0.47
     laboratories
    0.47
     Southeast
    0.43
    States
    0.43
    लया
    0.43
    ल
    0.43
     Ibn
    0.43
     module
    0.43
        
    0.42
     environment
    0.42
    POSITIVE LOGITS
    繹
    0.49
    чы
    0.47
    蚀
    0.45
    دي
    0.44
    感情
    0.44
    喜剧
    0.44
     بالم
    0.43
    自殺
    0.43
    罵
    0.43
     चिप
    0.42
    Act Density 0.001%

    No Known Activations