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

    Neuronpedia

    INDEX
    Explanations

    search, find, filter

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     unlocked
    0.37
     Ministry
    0.36
     audited
    0.36
     treating
    0.36
     myself
    0.35
     khen
    0.35
     prevalent
    0.35
     bagging
    0.34
    我都
    0.34
     WAR
    0.34
    POSITIVE LOGITS
    検索
    0.49
    絞
    0.47
    导航
    0.46
    定位
    0.45
    Narrow
    0.44
    搜索
    0.43
     ठिका
    0.43
    过滤器
    0.42
     search
    0.41
    bilical
    0.41
    Act Density 0.002%

    No Known Activations