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

    Neuronpedia

    INDEX
    Explanations

    Note

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cuisine
    -0.07
    [player
    -0.06
    &R
    -0.06
    <U
    -0.06
     tpl
    -0.06
    unks
    -0.06
    にお
    -0.06
    .DataGridViewColumnHeadersHeightSizeMode
    -0.06
    endid
    -0.06
     towel
    -0.06
    POSITIVE LOGITS
    意味
    0.07
    (INFO
    0.07
     conse
    0.07
     Note
    0.06
    _edges
    0.06
     olay
    0.06
    ，其中
    0.06
     documented
    0.06
    ={[↵
    0.06
    "],"
    0.06
    Act Density 0.012%

    No Known Activations