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

    Neuronpedia

    INDEX
    Explanations

    noun followed by description

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    o
    1.03
    u
    1.01
    s
    1.00
    ar
    0.96
    us
    0.92
    R
    0.92
    IN
    0.91
    ↵
    0.91
    S
    0.90
    y
    0.88
    POSITIVE LOGITS
    ありません
    0.88
    ită
    0.83
    鍘
    0.82
     padrões
    0.82
    િંગ
    0.80
     výrob
    0.80
    ംഗ്
    0.80
    इड
    0.80
     especiais
    0.79
    يران
    0.78
    Act Density 0.206%

    No Known Activations