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

    Neuronpedia

    INDEX
    Explanations

    differential equations, neural networks, quantum mechanics, regression

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    I
    0.25
    na
    0.24
    आई
    0.23
    nae
    0.22
    gens
    0.22
    ंना
    0.21
    isions
    0.21
     sillä
    0.21
    s
    0.21
    1
    0.20
    POSITIVE LOGITS
    ת
    0.29
    ↵
    0.27
    ות
    0.25
     be
    0.23
     for
    0.22
    აწ
    0.22
     Mijn
    0.22
    ちゃんの
    0.22
     buses
    0.21
     player
    0.21
    Act Density 0.993%

    No Known Activations