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

    Neuronpedia

    INDEX
    Explanations

    Code syntax

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rock
    -0.07
     Rosen
    -0.07
     Resume
    -0.07
     surfaces
    -0.06
     FIN
    -0.06
     drugs
    -0.06
    Year
    -0.06
     occupancy
    -0.06
     MDB
    -0.06
    ен
    -0.06
    POSITIVE LOGITS
    .blur
    0.06
     строитель
    0.06
     　 　
    0.06
    ically
    0.06
     hdf
    0.06
    ▏
    0.06
    alamat
    0.06
    ?>↵↵↵
    0.06
    력이
    0.06
     　 　 　
    0.06
    Act Density 0.017%

    No Known Activations