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

    Neuronpedia

    INDEX
    Explanations

    map explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     spokesman
    0.50
    ണമെന്ന്
    0.48
     rifi
    0.48
    Widget
    0.46
     fifty
    0.46
     ടി
    0.45
     weapons
    0.44
     unanimous
    0.44
     Whiting
    0.44
     duties
    0.43
    POSITIVE LOGITS
    。
    0.63
    י
    0.50
    ки
    0.47
    ник
    0.47
    तरी
    0.47
    1
    0.47
    рии
    0.46
    ра
    0.46
    ми
    0.46
    за
    0.44
    Act Density 0.000%

    No Known Activations