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

    Neuronpedia

    INDEX
    Explanations

    sol followed by solitary, solitude, or solar

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     averages
    0.61
     AVERAGE
    0.58
     Average
    0.56
    Average
    0.54
     average
    0.52
    平均
    0.52
     Aver
    0.52
    average
    0.50
     평균
    0.49
     aver
    0.47
    POSITIVE LOGITS
    Sol
    1.02
     Sol
    0.97
     sol
    0.97
     SOL
    0.95
    SOL
    0.91
    sol
    0.84
     Сол
    0.78
     솔
    0.76
     сол
    0.75
     ソ
    0.75
    Act Density 0.014%

    No Known Activations