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

    Neuronpedia

    INDEX
    Explanations

    territorial divisions and titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    kings
    0.22
    ześ
    0.22
    러
    0.21
     princes
    0.21
     kings
    0.21
    hes
    0.21
    RF
    0.20
    ще
    0.20
    疆
    0.20
    uks
    0.19
    POSITIVE LOGITS
    🏚
    0.21
    ⛰
    0.21
     由于
    0.20
     reshape
    0.20
     因为
    0.20
    }_{-}\
    0.20
     因為
    0.19
    ⛴
    0.19
    Ⓜ
    0.19
    ợp
    0.19
    Act Density 0.005%

    No Known Activations