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

    Neuronpedia

    INDEX
    Explanations

    math and science concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     හැකි
    0.45
     ▲
    0.37
     ►
    0.37
     võivad
    0.37
    Char
    0.36
     جوړونکی
    0.36
    Among
    0.36
     Го
    0.36
    Here
    0.35
    ையடுத்து
    0.35
    POSITIVE LOGITS
    羍
    0.45
     proton
    0.44
    )];
    0.43
    䐂
    0.41
    耑
    0.41
    絬
    0.40
    )`
    0.40
    град
    0.39
    )`,
    0.39
     integrable
    0.39
    Act Density 0.051%

    No Known Activations