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

    Neuronpedia

    INDEX
    Explanations

    Poland, Pearl Harbor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.52
    文化
    0.43
     Cultural
    0.40
     cultural
    0.39
    ukai
    0.38
     \
    0.38
    这个时候
    0.37
    上一
    0.37
     Vai
    0.37
    侯
    0.36
    POSITIVE LOGITS
     kammam
    0.52
     dimiliki
    0.47
    𝙋
    0.46
     diámetro
    0.45
    ゴー
    0.45
    𒌇
    0.45
    ERCIAL
    0.45
    гам
    0.44
    鶉
    0.44
    濺
    0.44
    Act Density 0.001%

    No Known Activations