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

    Neuronpedia

    INDEX
    Explanations

    the significance of abstract nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    m
    1.21
    .
    1.03
     apaixon
    0.90
     others
    0.88
     dimers
    0.88
     cufflinks
    0.87
     spouse
    0.82
     haupt
    0.81
    ING
    0.80
     sauerkraut
    0.80
    POSITIVE LOGITS
    ación
    1.06
    zione
    1.02
    丆
    1.02
     кількість
    1.01
     ອ
    1.00
    ínio
    0.98
    quantidade
    0.97
    ittäin
    0.96
    èle
    0.96
    icación
    0.96
    Act Density 0.424%

    No Known Activations