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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Victim
    -0.08
    /dr
    -0.07
     Western
    -0.06
    Zen
    -0.06
     Coun
    -0.06
     таких
    -0.06
     sır
    -0.06
    Naz
    -0.06
    .self
    -0.06
    들에게
    -0.06
    POSITIVE LOGITS
     مشخص
    0.07
    period
    0.06
     квітня
    0.06
    สะ
    0.06
    バ
    0.06
     merit
    0.06
    Latitude
    0.06
     Cary
    0.06
    ]:↵↵
    0.06
    チャ
    0.06
    Act Density 0.047%

    No Known Activations