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

    Neuronpedia

    INDEX
    Explanations

    cherish, loyal, livestock

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     있지만
    0.59
    相比
    0.50
    avgsalary
    0.50
    भिन्न
    0.49
    但在
    0.48
     зара
    0.47
     impediments
    0.46
     inmig
    0.46
    FhirExtension
    0.46
     रहता
    0.45
    POSITIVE LOGITS
     R
    0.70
     P
    0.68
     T
    0.61
     B
    0.61
     M
    0.61
     S
    0.59
     V
    0.59
    '
    0.59
     D
    0.57
     Burgers
    0.57
    Act Density 0.003%

    No Known Activations