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

    Neuronpedia

    INDEX
    Explanations

    roles and professions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     utilizando
    0.49
     pomocí
    0.47
     softmax
    0.47
     disson
    0.47
     diurnal
    0.47
    を用いる
    0.47
     afbeelding
    0.47
     gunakan
    0.46
     allure
    0.46
     subtypes
    0.46
    POSITIVE LOGITS
     lawyer
    0.65
     attorney
    0.64
     адво
    0.59
     solicitor
    0.55
     psychiatrist
    0.55
     congressman
    0.54
    律师
    0.54
     photographer
    0.53
     Attorney
    0.52
     accountant
    0.52
    Act Density 0.034%

    No Known Activations