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

    Neuronpedia

    INDEX
    Explanations

    describes capabilities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    این
    0.18
     yapacağız
    0.17
     أو
    0.17
     olacaktır
    0.17
     harán
    0.17
     هذا
    0.16
     nebo
    0.16
     seront
    0.15
    خواهد
    0.15
     serão
    0.15
    POSITIVE LOGITS
     arguably
    0.21
     also
    0.20
     intricately
    0.19
     requires
    0.17
     employs
    0.17
     relies
    0.17
     accomplished
    0.17
     introduces
    0.16
     A
    0.16
     invariably
    0.16
    Act Density 1.047%

    No Known Activations