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

    Neuronpedia

    INDEX
    Explanations

    they

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ilebilir
    -0.07
     зим
    -0.07
     Asphalt
    -0.07
     roof
    -0.06
     TOTAL
    -0.06
    _schema
    -0.06
     次
    -0.06
     produtos
    -0.06
     دور
    -0.06
     crave
    -0.06
    POSITIVE LOGITS
     المنت
    0.07
    InnerHTML
    0.06
     Disc
    0.06
    InstantiationException
    0.06
     resumes
    0.06
     Druid
    0.06
     gramm
    0.06
     등의
    0.06
     constitu
    0.06
    _memcpy
    0.06
    Act Density 0.000%

    No Known Activations