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

    Neuronpedia

    INDEX
    Explanations

    Chinese names and phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    储备
    0.44
    缬
    0.43
    Monitoring
    0.43
    altering
    0.41
    Rationale
    0.41
    Assets
    0.41
     noirâtres
    0.41
    Analysis
    0.41
    Rescue
    0.40
    閾
    0.40
    POSITIVE LOGITS
     WeChat
    0.80
     Qian
    0.77
     Sichuan
    0.75
     Weibo
    0.75
     Xiao
    0.75
     netizens
    0.73
     Chinese
    0.71
     Xia
    0.70
     Jiang
    0.69
     Qing
    0.69
    Act Density 0.021%

    No Known Activations