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

    Neuronpedia

    INDEX
    Explanations

    punctuation and line breaks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Gordon
    0.39
    ﻤ
    0.38
    list
    0.38
     Gordon
    0.38
     SVG
    0.37
    label
    0.36
     labeling
    0.36
    ="{{
    0.35
     Fourier
    0.35
     tet
    0.34
    POSITIVE LOGITS
    鐗
    0.42
    くる
    0.40
    बंग
    0.37
    cnty
    0.36
     ಅಂಗ
    0.36
    ngth
    0.36
     جماعه
    0.36
    чени
    0.35
    띵
    0.35
     आढळ
    0.35
    Act Density 0.000%

    No Known Activations