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

    Neuronpedia

    INDEX
    Explanations

    definition of law

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ς
    0.58
    ϓ
    0.51
    ンの
    0.50
     şark
    0.49
     δεί
    0.48
     maksimum
    0.48
    やすく
    0.48
    ۳
    0.48
    トート
    0.47
    ों
    0.47
    POSITIVE LOGITS
    rier
    0.44
     Burr
    0.43
     Derr
    0.42
     Bus
    0.42
    erp
    0.41
     Region
    0.40
     Law
    0.40
     Bur
    0.39
    er
    0.39
    erne
    0.39
    Act Density 0.006%

    No Known Activations