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

    Neuronpedia

    INDEX
    Explanations

    AI 助手 Chinese model

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     swoim
    0.86
    ᱛ
    0.86
    ┝
    0.82
    ся
    0.81
             
    0.80
    ble
    0.79
     Kya
    0.78
    枼
    0.77
              
    0.77
    אל
    0.77
    POSITIVE LOGITS
     რომ
    0.86
    往下
    0.86
    gpu
    0.78
     людьми
    0.78
     hubo
    0.78
     terrib
    0.78
     resistente
    0.77
     worse
    0.76
    ッカー
    0.76
    会い
    0.76
    Act Density 0.000%

    No Known Activations