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

    Neuronpedia

    INDEX
    Explanations

    thinking about models

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     идеа
    0.46
     Diwali
    0.46
     скла
    0.45
     δημο
    0.43
     партии
    0.43
     पहा
    0.43
     artistes
    0.43
    ters
    0.42
     Entrepreneur
    0.42
    anians
    0.42
    POSITIVE LOGITS
    ウェア
    0.46
     coolant
    0.46
    েষে
    0.44
     sealant
    0.44
     Daley
    0.44
    렌
    0.42
     élytres
    0.42
     Egan
    0.42
    injection
    0.41
     nowy
    0.41
    Act Density 0.006%

    No Known Activations