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

    Neuronpedia

    INDEX
    Explanations

    appear/look

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    食べて
    -0.07
     Baron
    -0.07
     await
    -0.07
    <nav
    -0.07
    是韩国
    -0.07
    浼
    -0.07
    .ag
    -0.07
     stormed
    -0.07
    玷
    -0.07
    뛔
    -0.07
    POSITIVE LOGITS
    .Resume
    0.07
    //
    0.07
     supplemental
    0.07
    थ
    0.07
    뺍
    0.07
    leaf
    0.07
     objects
    0.07
    ኸ
    0.07
     AppBar
    0.07
     \<^
    0.06
    Act Density 0.014%

    No Known Activations