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

    Neuronpedia

    INDEX
    Explanations

    programming questions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    当然
    -0.07
    \
↵
    -0.07
    беж
    -0.07
    一起来
    -0.07
    (ERROR
    -0.07
    𝜔
    -0.07
    {x
    -0.06
    .setX
    -0.06
     לנ
    -0.06
    可是
    -0.06
    POSITIVE LOGITS
     hauling
    0.08
    车企
    0.07
    ｹ
    0.07
    .Charting
    0.07
    	edit
    0.07
     Garage
    0.07
     reign
    0.07
     wastes
    0.07
     tug
    0.06
    口感
    0.06
    Act Density 0.093%

    No Known Activations