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

    Neuronpedia

    INDEX
    Explanations

    statistical text generation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     archaeological
    0.80
     Q
    0.69
     Sphere
    0.69
     shrimp
    0.69
     sphere
    0.66
     events
    0.66
     Vogue
    0.65
     Dear
    0.65
     scholarship
    0.65
     आस्था
    0.64
    POSITIVE LOGITS
    빱
    0.79
    otas
    0.77
    ിട
    0.70
    ्यु
    0.69
     ईमानदारी
    0.68
     නි
    0.66
    㨁
    0.64
    𝙚
    0.64
    ētu
    0.64
     বণ্ট
    0.64
    Act Density 0.007%

    No Known Activations