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

    Neuronpedia

    INDEX
    Explanations

    software development plugins

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    h
    0.56
     नेपाल
    0.50
     Secretary
    0.50
     মহাসচিব
    0.49
    缟
    0.49
    体
    0.48
     Rishi
    0.48
    。
    0.48
     मंजिल
    0.47
     Département
    0.47
    POSITIVE LOGITS
    م
    0.77
    plug
    0.70
    א
    0.70
     plugins
    0.64
     plugs
    0.63
    на
    0.61
    plugins
    0.57
    插件
    0.56
     anunciar
    0.56
    အတ
    0.55
    Act Density 0.015%

    No Known Activations