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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .actor
    -0.08
    %'↵
    -0.07
    OMBRE
    -0.07
    Code
    -0.07
    노동
    -0.07
     BO
    -0.07
     pension
    -0.07
    _image
    -0.07
    .reshape
    -0.07
    _sh
    -0.06
    POSITIVE LOGITS
    لق
    0.07
     אית
    0.07
     использовать
    0.07
    时机
    0.07
    祎
    0.07
    *time
    0.07
    ียง
    0.07
    яв
    0.07
    zed
    0.06
     ListItem
    0.06
    Act Density 0.007%

    No Known Activations