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

    Neuronpedia

    INDEX
    Explanations

    reaching out for help

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    io
    0.56
     (
    0.56
     যাতে
    0.55
    出色
    0.52
     อะไร
    0.49
    يا
    0.49
     باعث
    0.48
    ë
    0.48
    p
    0.47
     मुताबिक
    0.47
    POSITIVE LOGITS
    Alternatives
    0.56
    Klein
    0.56
    McK
    0.56
    Translations
    0.55
    astien
    0.55
    PayPal
    0.55
     tzv
    0.54
    ोसिएशन
    0.54
    geek
    0.54
     Groupon
    0.52
    Act Density 0.184%

    No Known Activations