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

    Neuronpedia

    INDEX
    Explanations

    context length and date

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    "".
    0.46
    㳊
    0.45
    拙
    0.45
    ित्र
    0.45
    "。
    0.45
    .。
    0.44
    }}.
    0.43
    。"
    0.42
    "};
    0.41
    。(
    0.41
    POSITIVE LOGITS
     chuy
    0.54
     año
    0.48
     brothers
    0.48
     llegó
    0.48
    ólnie
    0.48
     pulverized
    0.47
     árbol
    0.47
     Sơn
    0.47
     viện
    0.46
    áns
    0.46
    Act Density 0.006%

    No Known Activations