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

    Neuronpedia

    INDEX
    Explanations

    generalization and variation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dosages
    0.42
     hugs
    0.41
     hogs
    0.41
     pharmaceutical
    0.40
     dosage
    0.39
     hầu
    0.39
     pharma
    0.39
     deaths
    0.38
     disipl
    0.38
     bruises
    0.38
    POSITIVE LOGITS
    Stere
    0.52
    Individual
    0.42
    Grass
    0.42
    Diversity
    0.41
    rift
    0.41
    Alternatives
    0.41
    郧
    0.41
     문화
    0.41
    Gust
    0.40
    ર
    0.39
    Act Density 0.161%

    No Known Activations