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

    Neuronpedia

    INDEX
    Explanations

    summer olympics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     zobowiąz
    -0.07
    CLEAR
    -0.07
    כס
    -0.07
    닮
    -0.06
    ꓽ
    -0.06
    Phill
    -0.06
    מטופל
    -0.06
    .Exec
    -0.06
     Sr
    -0.06
     שימוש
    -0.06
    POSITIVE LOGITS
    >"↵
    0.07
     disclosures
    0.07
     zien
    0.07
    0.06
    🎨
    0.06
    0.06
    ureau
    0.06
    yun
    0.06
     Nội
    0.06
     lantern
    0.06
    Act Density 0.004%

    No Known Activations