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

    Neuronpedia

    INDEX
    Explanations

    related to 'we' and 'you'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    starts
    0.82
     زمن
    0.77
     Traffic
    0.76
    غ
    0.74
     NRG
    0.74
    م
    0.74
    environmental
    0.73
    un
    0.72
    iba
    0.71
    ends
    0.71
    POSITIVE LOGITS
     passende
    0.99
    ,((
    0.97
    শিত
    0.95
     achten
    0.92
     fün
    0.91
     conseille
    0.90
     leisten
    0.90
     suis
    0.86
     mewah
    0.86
     mitophagy
    0.86
    Act Density 0.000%

    No Known Activations