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

    Neuronpedia

    INDEX
    Explanations

    by Google

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Wordsworth
    0.55
     作者
    0.54
     ஜெ
    0.49
     polskich
    0.49
     ભારત
    0.47
    E
    0.47
     Bruce
    0.47
     영국
    0.46
    ات
    0.45
     deutscher
    0.45
    POSITIVE LOGITS
    :
    0.51
    :}
    0.44
     manpower
    0.40
    Становништво
    0.39
     shrinkage
    0.39
     elongation
    0.38
          
    0.37
     ενεργ
    0.37
     \\
    0.37
    </h2>
    0.37
    Act Density 0.031%

    No Known Activations