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

    Neuronpedia

    INDEX
    Explanations

    type

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    াতাড়ি
    0.50
    sı
    0.47
    ₫
    0.44
    sü
    0.43
    τρο
    0.42
     দূর
    0.42
    ról
    0.42
    sunday
    0.42
    ্সে
    0.41
     mauvaise
    0.41
    POSITIVE LOGITS
     kelamin
    0.79
     type
    0.79
    Types
    0.77
    Type
    0.77
     types
    0.76
     类型
    0.73
     Type
    0.71
     getType
    0.70
    类型
    0.67
     TYPE
    0.67
    Act Density 0.032%

    No Known Activations