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

    Neuronpedia

    INDEX
    Explanations

    makes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ập
    -0.07
     hlavu
    -0.07
    IDGET
    -0.06
    vů
    -0.06
    ของผ
    -0.06
     shading
    -0.06
    xFFFF
    -0.06
    伯
    -0.06
    فع
    -0.06
    =[],
    -0.06
    POSITIVE LOGITS
    {↵
    0.07
    adin
    0.07
    {↵↵
    0.06
    <j
    0.06
    orses
    0.06
    (bg
    0.06
     {↵
    0.06
    Transfer
    0.06
    Different
    0.06
    FORE
    0.06
    Act Density 0.359%

    No Known Activations