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

    Neuronpedia

    INDEX
    Explanations

    Portugal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    path
    0.84
    body
    0.84
    valor
    0.74
     まし
    0.72
    न्दगी
    0.72
    Τ
    0.72
    כ
    0.71
    Μ
    0.70
    clean
    0.69
    command
    0.68
    POSITIVE LOGITS
     Dade
    0.90
    बद्ध
    0.85
     Brune
    0.83
     triangles
    0.83
     trimethyl
    0.78
     deportes
    0.77
     kilograms
    0.76
     Triangle
    0.76
    ದುಕೊಳ್ಳ
    0.76
    ды
    0.75
    Act Density 0.002%

    No Known Activations