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

    Neuronpedia

    INDEX
    Explanations

    offering help if you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    די
    0.50
    du
    0.49
    de
    0.49
    L
    0.48
     statewide
    0.47
    m
    0.46
    太
    0.44
    G
    0.44
    熱
    0.44
    热
    0.43
    POSITIVE LOGITS
     extrema
    0.52
    тли
    0.52
     ними
    0.50
     импе
    0.47
     कार्यकर्
    0.45
     tumour
    0.45
    шенко
    0.45
     núcle
    0.44
     কমপক্ষে
    0.44
     них
    0.44
    Act Density 0.003%

    No Known Activations