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

    Neuronpedia

    INDEX
    Explanations

    lambda with key for sorting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    心中
    0.41
     सिव
    0.40
    lept
    0.40
    壟
    0.38
     marathon
    0.38
     ስለዚህ
    0.38
    ランキング
    0.38
    ørte
    0.37
    邮
    0.37
    婧
    0.37
    POSITIVE LOGITS
     lambda
    1.03
    lambda
    0.90
     λ
    0.73
    λ
    0.68
     Lambda
    0.65
    𝜆
    0.61
     lamb
    0.59
     identity
    0.58
    Lambda
    0.56
     Identity
    0.53
    Act Density 0.009%

    No Known Activations