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

    Neuronpedia

    INDEX
    Explanations

    science

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    화를
    -0.07
    ิต
    -0.07
    交
    -0.06
    polit
    -0.06
    ذكر
    -0.06
    ้นท
    -0.06
     opioids
    -0.06
    ợi
    -0.06
    휴
    -0.06
    лося
    -0.06
    POSITIVE LOGITS
     imagePath
    0.07
    ：↵↵
    0.07
    !')↵↵
    0.06
     swingerclub
    0.06
    [,]
    0.06
     hwnd
    0.06
    _when
    0.06
    _typeDefinitionSize
    0.06
    ↵				↵
    0.06
    ата
    0.06
    Act Density 0.196%

    No Known Activations