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

    Neuronpedia

    INDEX
    Explanations

    closing salutations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    शी
    0.78
    anzitutto
    0.70
     thrice
    0.69
    नाच्या
    0.68
     best
    0.68
     revive
    0.65
     तीन
    0.62
    ப்பட்ட
    0.61
     অন্তঃ
    0.61
     তিনটি
    0.60
    POSITIVE LOGITS
    ==-
    0.92
     Branding
    0.86
     деятельности
    0.86
    ,/
    0.85
     Activities
    0.85
     Thomas
    0.84
     Kavanaugh
    0.84
     injuries
    0.84
    ↵↵
    0.83
     hiểm
    0.83
    Act Density 0.026%

    No Known Activations