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

    Neuronpedia

    INDEX
    Explanations

    website urls and country codes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     😍
    0.26
     Roblox
    0.26
     😏
    0.25
     Mfg
    0.25
     😁
    0.25
    性价比
    0.24
     最大
    0.24
     neckline
    0.24
     nhất
    0.24
    字节
    0.24
    POSITIVE LOGITS
    that
    0.28
    and
    0.27
    mer
    0.25
    an
    0.24
    P
    0.24
    rel
    0.23
    had
    0.23
    R
    0.23
    を中心
    0.23
    C
    0.23
    Act Density 0.045%

    No Known Activations