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

    Neuronpedia

    INDEX
    Explanations

    scientists and doctors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     অমিত
    0.38
     wastes
    0.38
    หย
    0.38
    เท่า
    0.37
     реклам
    0.37
    authorization
    0.37
    anguage
    0.37
     advertising
    0.36
     মোর
    0.36
     corrente
    0.36
    POSITIVE LOGITS
     ecologists
    0.77
     biologist
    0.70
     ec
    0.68
     scientist
    0.68
     scientists
    0.65
     Scientist
    0.63
    Scientists
    0.62
     Scientists
    0.61
     biologists
    0.60
     Dr
    0.56
    Act Density 0.001%

    No Known Activations