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

    Neuronpedia

    INDEX
    Explanations

    /*

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ы
    -0.07
    ULK
    -0.07
     mention
    -0.06
    Dictionary
    -0.06
    [result
    -0.06
     "#"
    -0.06
     bullish
    -0.06
    used
    -0.06
    ตะ
    -0.06
    UAGE
    -0.06
    POSITIVE LOGITS
     chops
    0.07
    생활
    0.07
    `);↵↵
    0.07
    vements
    0.07
     {};↵
    0.07
     выгляд
    0.07
    ↵↵↵
    0.06
     сир
    0.06
     фін
    0.06
    搭
    0.06
    Act Density 0.011%

    No Known Activations