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

    Neuronpedia

    INDEX
    Explanations

    parentheses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     HB
    -0.07
    鸟成长记
    -0.07
    räu
    -0.07
    חב
    -0.06
    蹅
    -0.06
    糇
    -0.06
    ard
    -0.06
    't
    -0.06
     overhaul
    -0.06
     henüz
    -0.06
    POSITIVE LOGITS
     Lowell
    0.07
    ユニ
    0.07
    räg
    0.07
     Россий
    0.07
    粉色
    0.07
     Sh
    0.07
    ちら
    0.07
    比利时
    0.07
     النظام
    0.07
     Anonymous
    0.07
    Act Density 0.006%

    No Known Activations