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

    Neuronpedia

    INDEX
    Explanations

    sections of acts or laws

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ysh
    0.40
    тивной
    0.39
     uart
    0.38
    위에
    0.38
     Parch
    0.36
    uela
    0.36
    propylene
    0.36
    üne
    0.35
    ),\\
    0.35
    ).\\
    0.34
    POSITIVE LOGITS
     நம்பிக்கை
    0.39
    čných
    0.37
    Фе
    0.37
    чки
    0.37
     બંને
    0.36
     நம்பிக்க
    0.36
     Complex
    0.35
     Bhub
    0.35
     stork
    0.35
     Lour
    0.34
    Act Density 0.002%

    No Known Activations