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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    伞
    -0.08
    村子
    -0.07
    沖
    -0.07
    徐州
    -0.07
     Çünkü
    -0.07
    沉迷
    -0.07
     excitement
    -0.07
    情感
    -0.07
    旸
    -0.07
    ȩ
    -0.07
    POSITIVE LOGITS
    承办
    0.06
    .navigationController
    0.06
    EventHandler
    0.06
    original
    0.06
    Tick
    0.06
     Asked
    0.06
    🔑
    0.06
     Checker
    0.06
    Synopsis
    0.06
    五四
    0.06
    Act Density 0.000%

    No Known Activations