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

    Neuronpedia

    INDEX
    Explanations

    doesn't

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    agram
    0.35
     sein
    0.35
    于是
    0.34
    んですが
    0.33
    ′,
    0.33
    <0xB1>
    0.32
    Figures
    0.30
    ដែល
    0.30
     Magento
    0.30
    ō
    0.30
    POSITIVE LOGITS
    െ
    0.37
    rène
    0.36
    таў
    0.36
    0.36
     gelar
    0.35
    нні
    0.35
    чені
    0.34
    rakech
    0.34
     onus
    0.33
     CLL
    0.33
    Act Density 0.275%

    No Known Activations