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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fname
    -0.06
     camb
    -0.06
    .Named
    -0.06
     مطالعه
    -0.06
    �
    -0.06
     definitive
    -0.06
    _dataframe
    -0.06
    わ
    -0.06
    }>↵
    -0.06
    確認
    -0.05
    POSITIVE LOGITS
    .references
    0.07
    .NOT
    0.07
    출장안마
    0.06
    	rep
    0.06
    0.06
     Laptop
    0.06
    wav
    0.06
     تلك
    0.06
    exampleInputEmail
    0.06
    reek
    0.06
    Act Density 0.011%

    No Known Activations