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

    Neuronpedia

    INDEX
    Explanations

    Purpose, money, and requests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     convertir
    0.39
    凯
    0.39
     dr
    0.39
    Radiux
    0.38
    Вакансия
    0.38
    待
    0.38
     sighted
    0.37
    لیل
    0.37
     meet
    0.37
     poc
    0.37
    POSITIVE LOGITS
    Purpose
    0.52
     Purpose
    0.49
    purpose
    0.48
     variation
    0.47
     Variation
    0.46
    Variation
    0.43
     Variations
    0.43
     variations
    0.43
    Abstract
    0.42
    variation
    0.41
    Act Density 0.000%

    No Known Activations