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

    Neuronpedia

    INDEX
    Explanations

    recipes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     такое
    -0.07
    etadata
    -0.06
    'al
    -0.06
     basin
    -0.06
    TableModel
    -0.06
    プロ
    -0.06
     маши
    -0.06
    虽然
    -0.06
     McKenzie
    -0.06
     اولیه
    -0.06
    POSITIVE LOGITS
    (term
    0.07
     Δή
    0.06
     فتح
    0.06
    hdr
    0.06
     xyz
    0.06
     ()
    0.06
     Blockly
    0.06
    Books
    0.06
    auss
    0.06
    /vue
    0.06
    Act Density 0.007%

    No Known Activations