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

    Neuronpedia

    INDEX
    Explanations

    expects or predicts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    еди
    0.40
     बैठकर
    0.39
     점에서
    0.39
    lastKey
    0.38
    Keys
    0.37
    ដែល
    0.37
    keys
    0.37
    놔
    0.36
     따라서
    0.36
     값이
    0.36
    POSITIVE LOGITS
     naut
    0.45
     expects
    0.43
     Ach
    0.41
     EXPECT
    0.41
     oček
    0.41
    UJ
    0.41
     zouden
    0.40
     مزد
    0.40
     Asw
    0.39
     expect
    0.39
    Act Density 0.000%

    No Known Activations