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

    Neuronpedia

    INDEX
    Explanations

    Process

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (gca
    -0.08
    rails
    -0.07
    	product
    -0.07
    样子
    -0.07
     Responsibility
    -0.07
    스터
    -0.07
    図
    -0.07
    ESPN
    -0.07
     Swarm
    -0.07
    /bower
    -0.06
    POSITIVE LOGITS
     tim
    0.07
    lou
    0.06
     іде
    0.06
     reviewed
    0.06
     sire
    0.06
     Melbourne
    0.06
     }];↵
    0.05
    -he
    0.05
    》↵
    0.05
    	cin
    0.05
    Act Density 0.017%

    No Known Activations