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

    Neuronpedia

    INDEX
    Explanations

    research papers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Easily
    -0.07
    委组织部
    -0.06
    惫
    -0.06
     phóng
    -0.06
    .Script
    -0.06
    Extract
    -0.06
    /controller
    -0.06
    Css
    -0.06
    IsValid
    -0.06
    itr
    -0.06
    POSITIVE LOGITS
    \)
    0.07
    _shapes
    0.07
     khỏi
    0.07
    Colon
    0.07
    :")↵
    0.07
     FACE
    0.06
    脑子
    0.06
     contro
    0.06
     ال
    0.06
     Nine
    0.06
    Act Density 0.069%

    No Known Activations