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

    Neuronpedia

    INDEX
    Explanations

    home environment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _shadow
    -0.09
     Coalition
    -0.08
     coat
    -0.08
     obedience
    -0.08
     shadow
    -0.08
    -shadow
    -0.08
     coalition
    -0.08
    包
    -0.07
     cuota
    -0.07
     Конт
    -0.07
    POSITIVE LOGITS
     hemma
    0.12
     stationary
    0.12
     zuhause
    0.10
     server
    0.10
    服务器
    0.10
     hjemme
    0.10
     בבית
    0.10
     дома
    0.09
     Hause
    0.09
    _Statics
    0.09
    Act Density 0.184%

    No Known Activations