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

    Neuronpedia

    INDEX
    Explanations

    a descriptive word

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ses
    0.40
    adina
    0.40
    Brother
    0.38
    mann
    0.38
    ête
    0.38
    ofs
    0.38
    eps
    0.37
    enko
    0.37
    brother
    0.36
    Zona
    0.36
    POSITIVE LOGITS
     Sporting
    0.48
     notable
    0.39
     notably
    0.39
    MORE
    0.39
    挑战
    0.39
     ट्रायल
    0.38
     deeply
    0.38
     participates
    0.38
     wearable
    0.38
     layering
    0.38
    Act Density 0.002%

    No Known Activations