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

    Neuronpedia

    INDEX
    Explanations

    transparency and honesty

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Marseille
    0.44
     光
    0.42
     删除
    0.39
     refraction
    0.39
     PyQt
    0.39
     discarding
    0.39
     Shandong
    0.39
     Strawberry
    0.38
    时长
    0.38
    蓖
    0.38
    POSITIVE LOGITS
    )=$
    0.48
    ITHUB
    0.47
    govt
    0.45
    IRM
    0.44
    adie
    0.43
    cumsum
    0.43
    llvm
    0.41
    openai
    0.41
    create
    0.40
    IFORN
    0.40
    Act Density 0.003%

    No Known Activations