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

    Neuronpedia

    INDEX
    Explanations

    suggesting potential actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝙪
    0.51
    ूर्
    0.43
    issage
    0.42
     nerve
    0.41
    ylsulfanyl
    0.41
     opportune
    0.41
     offent
    0.39
    ecological
    0.39
    yat
    0.39
    ॉक्स
    0.39
    POSITIVE LOGITS
    deque
    0.46
    Q
    0.39
    Д
    0.39
    ചെയ
    0.39
    廰
    0.39
    Customer
    0.38
     نہيں
    0.38
     بكل
    0.38
     convertView
    0.38
    S
    0.38
    Act Density 0.000%

    No Known Activations