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

    Neuronpedia

    INDEX
    Explanations

    install, upload, copy files

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ō
    0.31
    /
    0.29
    امل
    0.29
    -
    0.29
    ικό
    0.29
    xA
    0.29
    大
    0.29
    도를
    0.28
    エン
    0.28
     Blumen
    0.28
    POSITIVE LOGITS
    🚱
    0.32
    🤽
    0.31
    🕜
    0.30
    স্পতিবার
    0.29
    धपुर
    0.29
     devising
    0.29
     บอก
    0.29
     えっと
    0.29
     altres
    0.28
     thoſe
    0.28
    Act Density 0.023%

    No Known Activations