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

    Neuronpedia

    INDEX
    Explanations

    iform

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    沿
    -0.07
    狠
    -0.07
    concert
    -0.07
    抵
    -0.06
    校
    -0.06
     بن
    -0.06
    по
    -0.06
     gost
    -0.06
    鄑
    -0.06
    安置
    -0.06
    POSITIVE LOGITS
    .Out
    0.07
    ивания
    0.07
     FileManager
    0.07
     foundational
    0.07
     imageName
    0.07
    _LAYER
    0.07
    _environment
    0.06
    eprom
    0.06
    扩展
    0.06
    ㇰ
    0.06
    Act Density 0.002%

    No Known Activations