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

    Neuronpedia

    INDEX
    Explanations

    blog posts/articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    osp
    -0.07
    ้ใน
    -0.07
    ("|
    -0.06
     Rotterdam
    -0.06
    Sequential
    -0.06
     července
    -0.06
     était
    -0.06
     steward
    -0.06
     fikir
    -0.06
     який
    -0.06
    POSITIVE LOGITS
    _random
    0.06
    식
    0.06
    伯
    0.06
    mitter
    0.06
     crit
    0.06
    (CancellationToken
    0.06
    imonial
    0.06
    isnan
    0.06
     veter
    0.06
     arte
    0.06
    Act Density 0.537%

    No Known Activations