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

    Neuronpedia

    INDEX
    Explanations

    reading files ('r')

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     নিয়মিত
    0.80
    Localization
    0.72
     原子
    0.70
     मार्क
    0.70
     برابر
    0.69
     표
    0.69
     regularmente
    0.68
    TextAlign
    0.68
     anlamına
    0.68
    Regular
    0.68
    POSITIVE LOGITS
     tonnes
    0.71
    ড়
    0.68
    Ț
    0.65
    irds
    0.64
     dead
    0.61
    फोन
    0.60
    rals
    0.59
    션을
    0.57
     попа
    0.57
     condensed
    0.57
    Act Density 0.004%

    No Known Activations