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

    Neuronpedia

    INDEX
    Explanations

    namespace

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ceilings
    -0.07
    lemetry
    -0.07
     ceiling
    -0.07
     download
    -0.06
    　　 　 　 　 　
    -0.06
    document
    -0.06
    )get
    -0.06
     where
    -0.06
    ено
    -0.06
     concludes
    -0.06
    POSITIVE LOGITS
    _OC
    0.08
    ilver
    0.06
     stiff
    0.06
    AZY
    0.06
     сторін
    0.06
     jeux
    0.06
     intact
    0.06
     臺
    0.06
    ايي
    0.06
    チ
    0.06
    Act Density 0.153%

    No Known Activations