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

    Neuronpedia

    INDEX
    Explanations

    sentence endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kug
    0.72
     recently
    0.70
     been
    0.70
     everything
    0.69
     récente
    0.67
    ళి
    0.67
     বৃহত্তম
    0.67
     einmal
    0.66
    糖尿病
    0.66
    आधार
    0.65
    POSITIVE LOGITS
    Coal
    0.68
    Poll
    0.67
    laughs
    0.67
     Gemma
    0.67
    Political
    0.63
     Rocky
    0.62
     Luego
    0.61
    CommandHandler
    0.61
    Evil
    0.61
    aded
    0.60
    Act Density 0.202%

    No Known Activations