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
    �
    -0.07
    total
    -0.06
    .header
    -0.06
     Notification
    -0.06
    _statement
    -0.06
    itive
    -0.06
    总
    -0.06
     Assertions
    -0.06
    願
    -0.06
     hele
    -0.06
    POSITIVE LOGITS
    `.`
    0.07
     nederland
    0.06
    /save
    0.06
    ErrorMsg
    0.06
    방
    0.06
    (errors
    0.06
     싱
    0.06
    .neo
    0.06
     brit
    0.06
    lake
    0.06
    Act Density 0.089%

    No Known Activations