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

    Neuronpedia

    INDEX
    Explanations

    ention

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Hos
    -0.07
     thăm
    -0.07
     הבאים
    -0.07
     Bon
    -0.07
    ند
    -0.07
    率先
    -0.07
    ﻥ
    -0.07
    فى
    -0.07
     thưởng
    -0.06
    sand
    -0.06
    POSITIVE LOGITS
     QUICK
    0.08
    -archive
    0.08
     ",";↵
    0.08
    allocated
    0.07
     EDT
    0.07
     getMax
    0.07
    Relation
    0.07
     proudly
    0.07
    .fail
    0.07
     ----------
    0.07
    Act Density 0.002%

    No Known Activations