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

    Neuronpedia

    INDEX
    Explanations

    advocate, advocacy, advise

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ೈನ್
    0.38
    に至
    0.38
    ặp
    0.37
     champion
    0.37
     கிரக
    0.37
    typical
    0.36
     文章
    0.35
    stool
    0.35
    的支持
    0.35
     stol
    0.35
    POSITIVE LOGITS
    Adv
    0.79
     adv
    0.71
     Adv
    0.69
    ocate
    0.69
     ADV
    0.66
    adv
    0.63
     Advocate
    0.63
    ocado
    0.62
    ADV
    0.61
    ogado
    0.59
    Act Density 0.004%

    No Known Activations