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

    Neuronpedia

    INDEX
    Explanations

    Google Books references

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pouring
    -0.07
     jungle
    -0.07
    ערכת
    -0.07
    仲裁
    -0.07
    卤
    -0.07
     khẳng
    -0.07
    粥
    -0.06
     pulumi
    -0.06
    驰
    -0.06
    .Child
    -0.06
    POSITIVE LOGITS
     الأمريكي
    0.07
    会影响到
    0.07
     changed
    0.06
    .project
    0.06
    PYTHON
    0.06
    社会稳定
    0.06
    gi
    0.06
    gems
    0.06
     fetisch
    0.06
    getRequest
    0.06
    Act Density 0.001%

    No Known Activations