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

    Neuronpedia

    INDEX
    Explanations

    resetting or restoring to defaults

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     যোগ্য
    0.41
     tapered
    0.40
     फ्रैक्शन
    0.39
    лимпий
    0.38
     tapering
    0.38
     isEmpty
    0.38
    وى
    0.38
     erythrocytes
    0.36
     süreç
    0.36
    淆
    0.35
    POSITIVE LOGITS
    settings
    0.90
     settings
    0.88
    defaults
    0.86
    Restore
    0.83
     Settings
    0.82
    Settings
    0.82
     restored
    0.81
     Restore
    0.81
     Defaults
    0.79
     restore
    0.78
    Act Density 0.006%

    No Known Activations