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

    Neuronpedia

    INDEX
    Explanations

    software errors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Максим
    -0.09
     maximizing
    -0.08
    Количество
    -0.08
     refurb
    -0.08
    ッグ
    -0.08
    owatt
    -0.08
     complac
    -0.08
    比例
    -0.08
     großzüg
    -0.08
    олю
    -0.08
    POSITIVE LOGITS
    缺
    0.13
     missing
    0.13
    _missing
    0.13
     Missing
    0.12
     fehlt
    0.12
    missing
    0.12
    Missing
    0.11
     fehlen
    0.11
     thiếu
    0.11
    找
    0.11
    Act Density 0.016%

    No Known Activations