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

    Neuronpedia

    INDEX
    Explanations

    even with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Styl
    0.50
    Bath
    0.50
    Dashboard
    0.49
    Diet
    0.48
    Maxim
    0.47
    Career
    0.46
    Quest
    0.46
    Tester
    0.45
    Utilities
    0.45
    Queensland
    0.45
    POSITIVE LOGITS
     القد
    0.73
     но
    0.73
     Но
    0.72
     Как
    0.71
     Если
    0.71
     disrespect
    0.66
     до
    0.66
    ர்க
    0.64
    泱
    0.62
    म्मत
    0.62
    Act Density 0.001%

    No Known Activations