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

    Neuronpedia

    INDEX
    Explanations

    cannot access

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Сі
    0.64
    าว
    0.53
    ЕН
    0.51
    ર્ક
    0.50
    Якщо
    0.50
    ৬
    0.49
    А
    0.48
    зку
    0.46
    리티
    0.46
    Пі
    0.45
    POSITIVE LOGITS
    oring
    0.46
    long
    0.45
     purify
    0.45
     cooperate
    0.44
    deserialize
    0.43
     bergerak
    0.42
     clase
    0.42
     запол
    0.42
     gubern
    0.41
     चैन
    0.41
    Act Density 0.000%

    No Known Activations