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

    Neuronpedia

    INDEX
    Explanations

    bullet points

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Adolf
    0.53
     Zhang
    0.48
     Liu
    0.46
     মিলিয়ন
    0.45
     Jiang
    0.44
    }\
    0.43
     creare
    0.43
     Industrie
    0.43
     ?
    0.42
     Zhao
    0.42
    POSITIVE LOGITS
     graz
    0.43
     назад
    0.43
     stopp
    0.42
    ENDING
    0.42
     ducks
    0.39
    ਥ
    0.38
    िडी
    0.38
     lambs
    0.38
    <unused54>
    0.37
     turkeys
    0.37
    Act Density 0.011%

    No Known Activations