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

    Neuronpedia

    INDEX
    Explanations

    code blocks and data fields

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AMES
    0.32
    плення
    0.32
    FORMAN
    0.29
    ॅम्प
    0.29
     হইয়াছিলেন
    0.29
    )-$
    0.29
    ANE
    0.29
    欬
    0.28
    デイ
    0.28
    ÔNG
    0.28
    POSITIVE LOGITS
    0.35
     shutil
    0.33
    itoa
    0.32
    <0x0D>
    0.31
    ".
    0.30
    redis
    0.30
    e
    0.30
    io
    0.29
    <0xE3>
    0.29
    item
    0.29
    Act Density 0.125%

    No Known Activations