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

    Neuronpedia

    INDEX
    Explanations

    percentages with decimal points

    oai_token-act-pair · gemini-2.0-flash

    Numerical results/measurements

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Data
    -0.61
     data
    -0.61
    aronder
    -0.60
    MENAFN
    -0.57
    Data
    -0.57
    WebVitals
    -0.57
    DataLoader
    -0.56
     csv
    -0.56
     Csv
    -0.56
    DATA
    -0.55
    POSITIVE LOGITS
     Dernière
    0.58
     BoxDecoration
    0.52
    BrowserModule
    0.52
     Konferenz
    0.51
    ViewFeatures
    0.49
     pageNum
    0.49
     costas
    0.47
     MainAxisSize
    0.47
     WaitForSeconds
    0.46
    amię
    0.46
    Act Density 0.641%

    No Known Activations