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

    Neuronpedia

    INDEX
    Explanations

    nuclear war

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    umann
    -0.07
     principio
    -0.07
     cowboy
    -0.07
    -program
    -0.07
     towns
    -0.07
    编号
    -0.06
     mobility
    -0.06
     monitored
    -0.06
    (directory
    -0.06
     têm
    -0.06
    POSITIVE LOGITS
    .persistence
    0.06
     veri
    0.06
     Km
    0.06
    _my
    0.06
     dislikes
    0.06
     Drag
    0.06
    .kernel
    0.06
    Shape
    0.06
     outside
    0.06
     hav
    0.05
    Act Density 0.043%

    No Known Activations