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

    Neuronpedia

    INDEX
    Explanations

    motivation and disincentives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     stric
    0.79
     기준으로
    0.78
     მარ
    0.73
    ፃ
    0.71
    찬가지
    0.70
     Strict
    0.70
     içeren
    0.69
     exclusivement
    0.69
    安置
    0.68
     기준
    0.67
    POSITIVE LOGITS
     motivation
    2.41
     motivated
    2.13
     Motivation
    2.11
     motivate
    2.10
    Motivation
    2.07
    motivation
    2.04
     motivates
    1.96
    motivated
    1.95
     motivación
    1.94
     incentive
    1.91
    Act Density 0.348%

    No Known Activations