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

    Neuronpedia

    INDEX
    Explanations

    stability in code and data processing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     out
    1.15
     COULD
    0.78
     Out
    0.78
    out
    0.77
     leech
    0.76
     innehåller
    0.74
    იმ
    0.74
     loser
    0.72
     lagen
    0.71
     Could
    0.70
    POSITIVE LOGITS
    Ghosts
    0.68
    वां
    0.67
    conc
    0.65
    iality
    0.65
     प्रति
    0.63
    ্‌
    0.62
    stability
    0.62
    स्वरूप
    0.61
    ്യ
    0.60
    罚
    0.60
    Act Density 0.488%

    No Known Activations