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

    Neuronpedia

    INDEX
    Explanations

    renewable energy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     inhibition
    -0.07
    چ
    -0.07
    Failure
    -0.07
    icon
    -0.07
     Abort
    -0.07
     Лю
    -0.06
     Origins
    -0.06
    acter
    -0.06
     skin
    -0.06
    du
    -0.06
    POSITIVE LOGITS
    .
↵
↵
    0.07
     Güney
    0.06
    ashire
    0.06
      ↵
    0.06
     theoret
    0.06
     Mandal
    0.06
    ヶ月
    0.06
     gutter
    0.06
       ↵
    0.06
    その他
    0.06
    Act Density 0.078%

    No Known Activations