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

    Neuronpedia

    INDEX
    Explanations

    foreign language and structured terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     आयात
    0.50
    dummy
    0.46
    ewhere
    0.45
    n
    0.45
    tiny
    0.44
     थोड़ी
    0.44
    imported
    0.43
    highlights
    0.43
    personal
    0.43
    dar
    0.43
    POSITIVE LOGITS
    严格
    0.50
     Jehová
    0.46
     strictly
    0.46
    Sans
    0.45
    Pour
    0.44
    去世
    0.44
     sí
    0.43
     chất
    0.43
    极其
    0.43
    ₃
    0.42
    Act Density 0.013%

    No Known Activations