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

    Neuronpedia

    INDEX
    Explanations

    -

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -padding
    -0.08
    (dictionary
    -0.08
    (border
    -0.08
     Virgin
    -0.07
    Technology
    -0.07
    =time
    -0.07
    _banner
    -0.07
     immigr
    -0.07
     scares
    -0.07
    гон
    -0.06
    POSITIVE LOGITS
     chân
    0.07
    Կ
    0.07
    约定
    0.07
     harsh
    0.07
     şek
    0.07
    orsk
    0.07
    家务
    0.07
    .Java
    0.06
    安全管理
    0.06
     чел
    0.06
    Act Density 0.002%

    No Known Activations