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

    Neuronpedia

    INDEX
    Explanations

    Fuel & oil

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    지는
    0.42
    Benefit
    0.41
     songwriting
    0.41
    ח
    0.41
    력이
    0.40
     surprise
    0.40
    ियां
    0.40
    이에
    0.40
    되는
    0.39
    하세요
    0.39
    POSITIVE LOGITS
     ihr
    0.46
    alers
    0.46
    fahren
    0.46
    nails
    0.46
    ্নান
    0.44
    haltens
    0.44
    দীর
    0.44
    prints
    0.44
    ]}/${
    0.43
    ciate
    0.43
    Act Density 0.001%

    No Known Activations