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

    Neuronpedia

    INDEX
    Explanations

    auto, automatic, auto-detection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    xpress
    0.44
     незакон
    0.44
    diy
    0.42
     Polymers
    0.42
    漣
    0.42
     visualisation
    0.41
     Outputs
    0.40
    ियल
    0.40
    зирован
    0.39
     단순히
    0.39
    POSITIVE LOGITS
     auto
    0.95
     automatically
    0.95
    auto
    0.93
    自动
    0.88
     автоматически
    0.81
     automatic
    0.79
     automaticamente
    0.79
    automatic
    0.78
    automatically
    0.78
    Automatically
    0.74
    Act Density 0.010%

    No Known Activations