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

    Neuronpedia

    INDEX
    Explanations

    amounts and limits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     phức
    0.37
     komplex
    0.35
     mecanismo
    0.34
     mekanisme
    0.34
     coûte
    0.33
     сущ
    0.32
     lành
    0.32
     getType
    0.32
    setType
    0.31
    mek
    0.31
    POSITIVE LOGITS
     numbers
    1.05
    數字
    0.92
    numbers
    0.91
    숫
    0.88
     숫
    0.84
     chiffres
    0.81
    数字
    0.80
     números
    0.78
     amount
    0.78
     cifra
    0.77
    Act Density 0.145%

    No Known Activations