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

    Neuronpedia

    INDEX
    Explanations

    legal documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    isko
    -0.07
    aremos
    -0.07
    ör
    -0.06
    .”↵↵
    -0.06
     ")";↵
    -0.06
     uploads
    -0.06
    ept
    -0.06
    l
    -0.06
     screened
    -0.06
    degree
    -0.06
    POSITIVE LOGITS
    _COLL
    0.07
     rů
    0.06
     الآ
    0.06
    .about
    0.06
     tartış
    0.06
    Almost
    0.06
    orestation
    0.06
     Filed
    0.06
     Presentation
    0.06
     pervasive
    0.06
    Act Density 0.007%

    No Known Activations