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

    Neuronpedia

    INDEX
    Explanations

    Wikipedia categories

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    όδ
    -0.06
     Concord
    -0.06
     Comput
    -0.06
     sham
    -0.06
    ____
    -0.06
     lawn
    -0.06
     n
    -0.06
    dire
    -0.06
    .cycle
    -0.06
     Trie
    -0.06
    POSITIVE LOGITS
     무슨
    0.07
    "url
    0.07
    _REL
    0.07
    Bel
    0.07
    ﻴ
    0.07
    
    0.06
    の一
    0.06
    strpos
    0.06
    変わ
    0.06
     разі
    0.06
    Act Density 0.018%

    No Known Activations