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

    Neuronpedia

    INDEX
    Explanations

    animal intelligence and ethology

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     угла
    0.41
     neden
    0.40
     Woo
    0.39
     असली
    0.39
    arium
    0.39
     suplement
    0.39
    ooled
    0.39
    lined
    0.39
     Sales
    0.38
    avin
    0.38
    POSITIVE LOGITS
     anarchist
    0.51
     anarch
    0.48
     abolition
    0.45
     autonom
    0.44
     comrades
    0.43
     compañ
    0.42
     communs
    0.40
     autonomy
    0.39
    刑
    0.39
     foragers
    0.39
    Act Density 0.056%

    No Known Activations