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

    Neuronpedia

    INDEX
    Explanations

    GB

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     verde
    -0.07
    れない
    -0.07
     순간
    -0.07
     Thomson
    -0.07
    碰撞
    -0.07
     unintended
    -0.07
     red
    -0.07
    	bytes
    -0.07
     bay
    -0.07
    rib
    -0.07
    POSITIVE LOGITS
     AAA
    0.07
    最基本的
    0.07
     February
    0.07
     Distribution
    0.07
    .fn
    0.07
    '},
↵
    0.07
    .ua
    0.07
    أحك
    0.06
     Pharmac
    0.06
    href
    0.06
    Act Density 0.002%

    No Known Activations