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

    Neuronpedia

    INDEX
    Explanations

    timestamps and legal citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mock
    0.46
    Mock
    0.44
    President
    0.41
     refuse
    0.41
     preparado
    0.41
     Mock
    0.40
     gathered
    0.39
     mocks
    0.39
     governor
    0.39
     Prepared
    0.39
    POSITIVE LOGITS
     тексто
    0.40
    ))%>%
    0.40
     Итак
    0.38
    --->
    0.38
     दुर्ग
    0.38
    ब्ल्यू
    0.37
    गाह
    0.37
     тексти
    0.36
    даго
    0.36
    createText
    0.36
    Act Density 0.001%

    No Known Activations