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

    Neuronpedia

    INDEX
    Explanations

    Monitoring and measurement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     хал
    -0.08
     section
    -0.08
     saint
    -0.08
    托
    -0.07
     lev
    -0.07
     seção
    -0.07
     الرئيس
    -0.07
     thy
    -0.07
    柴
    -0.07
    主义
    -0.07
    POSITIVE LOGITS
     diligent
    0.09
    -equipped
    0.09
     Enabled
    0.08
    (query
    0.08
     жүргіз
    0.08
     enabled
    0.08
     diagnostics
    0.08
     policing
    0.08
     Diagnostics
    0.08
     Displays
    0.08
    Act Density 0.317%

    No Known Activations