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

    Neuronpedia

    INDEX
    Explanations

    asking for help

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     НЕ
    0.38
     ܗ
    0.32
    的相关
    0.31
     ),
    0.31
     这个
    0.31
    (!)
    0.30
    Catagory
    0.30
     이는
    0.29
    에
    0.29
     этом
    0.29
    POSITIVE LOGITS
     anzi
    0.42
     meisten
    0.39
     viele
    0.38
     quente
    0.36
     membantu
    0.34
     soprattutto
    0.33
     muchos
    0.31
     sulit
    0.31
     convinced
    0.30
     moeil
    0.30
    Act Density 0.136%

    No Known Activations