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

    Neuronpedia

    INDEX
    Explanations

    combustion, King, unfolded, running

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    이가
    0.48
    tten
    0.47
    戏
    0.46
     १३
    0.46
    䔉
    0.46
    ە
    0.46
     сожалению
    0.45
    irittura
    0.45
    ቬ
    0.45
    大切な
    0.45
    POSITIVE LOGITS
     compound
    0.49
     glob
    0.48
    '
    0.45
     Compound
    0.44
     bolts
    0.44
     swap
    0.43
    िल्स
    0.41
     Conservation
    0.41
     piles
    0.41
     Sustainable
    0.40
    Act Density 0.004%

    No Known Activations