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

    Neuronpedia

    INDEX
    Explanations

    offers to help or continue

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ری
    0.26
     espectadores
    0.25
    ολ
    0.24
     cursos
    0.24
     अभ्यर्थियों
    0.24
    ยาน
    0.23
     दौरान
    0.23
     itp
    0.23
     attains
    0.23
    ।'
    0.23
    POSITIVE LOGITS
    請問
    0.42
     What
    0.40
    What
    0.37
     Какие
    0.37
     શું
    0.36
     ماذا
    0.34
    什么是
    0.34
    Какие
    0.32
     Why
    0.32
    what
    0.32
    Act Density 0.411%

    No Known Activations