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

    Neuronpedia

    INDEX
    Explanations

    money owed/wholesale

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Вікіпе
    -0.52
     pros
    -0.52
    pros
    -0.50
    ly
    -0.50
     mature
    -0.48
     Pros
    -0.48
     owed
    -0.47
    了
    -0.47
    Mature
    -0.47
    Pros
    -0.45
    POSITIVE LOGITS
     propOrder
    0.93
    Diweddarwch
    0.87
    AddTagHelper
    0.82
    LookAnd
    0.75
    featureID
    0.74
     <=",
    0.74
     betweenstory
    0.73
    DeleteBehavior
    0.73
     kasarigan
    0.71
    SequentialGroup
    0.66
    Act Density 0.144%

    No Known Activations