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

    Neuronpedia

    INDEX
    Explanations

    data automation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     xem
    -0.08
     gang
    -0.08
     nedenle
    -0.08
     मामले
    -0.08
     xan
    -0.07
     Ingen
    -0.07
     изб
    -0.07
    ائل
    -0.07
     deshalb
    -0.07
     derfor
    -0.07
    POSITIVE LOGITS
     automatisch
    0.15
     automatiquement
    0.14
     automáticamente
    0.14
     automaticamente
    0.13
     자동
    0.13
    自动
    0.13
     автоматически
    0.12
     Automatically
    0.12
     automatically
    0.12
     自动
    0.12
    Act Density 0.035%

    No Known Activations