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

    Neuronpedia

    INDEX
    Explanations

    language models

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    st
    0.48
    glyphs
    0.47
    न
    0.47
    ನಲ್ಲಿ
    0.47
     изделия
    0.46
     الفوت
    0.46
    ۰۰
    0.45
    rians
    0.45
    েই
    0.45
    rukt
    0.45
    POSITIVE LOGITS
     tiempos
    0.45
    ী
    0.43
    ฬ
    0.42
    高速
    0.42
     rapide
    0.42
     synthesizer
    0.41
     propulsion
    0.41
     प्रवास
    0.41
     churn
    0.40
    চেতন
    0.40
    Act Density 0.829%

    No Known Activations