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

    Neuronpedia

    INDEX
    Explanations

    above

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dign
    -0.07
    orn
    -0.07
    ﾄ
    -0.07
    ap
    -0.07
    rock
    -0.06
    choice
    -0.06
    hour
    -0.06
    	st
    -0.06
    вет
    -0.06
    桐
    -0.06
    POSITIVE LOGITS
     Ads
    0.07
     SAFE
    0.07
    .Max
    0.07
    592
    0.07
     ضد
    0.06
    =");↵
    0.06
     brilliant
    0.06
     expanding
    0.06
    .jsx
    0.06
     Television
    0.06
    Act Density 0.001%

    No Known Activations