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

    Neuronpedia

    INDEX
    Explanations

    AWS S3 configuration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Safety
    0.52
    Safety
    0.46
    Autom
    0.46
     Automation
    0.46
     ٹیکسٹ
    0.45
     safety
    0.43
     Data
    0.42
     Sicherheits
    0.42
     безопас
    0.42
     Automotive
    0.42
    POSITIVE LOGITS
     endothelial
    0.47
    ENDPOINT
    0.46
    retry
    0.46
    Retry
    0.45
    秉
    0.45
     endothelium
    0.45
    htt
    0.45
    httpClient
    0.45
    assaytype
    0.44
    エンド
    0.44
    Act Density 0.002%

    No Known Activations