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

    Neuronpedia

    INDEX
    Explanations

    explaining what something means

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Bakers
    0.47
    ือน
    0.46
     некоторых
    0.46
     někter
    0.45
     Algunas
    0.45
     Algunos
    0.44
     Einige
    0.43
     algumas
    0.43
     Ad
    0.42
    ア
    0.41
    POSITIVE LOGITS
     literalmente
    0.42
     savez
    0.41
     devastation
    0.40
     outperform
    0.40
     dubai
    0.39
     pau
    0.39
    unlike
    0.39
     весь
    0.38
     conquests
    0.38
    defendant
    0.38
    Act Density 0.026%

    No Known Activations