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

    Neuronpedia

    INDEX
    Explanations

    German language snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     espan
    -0.08
    igious
    -0.07
    费率
    -0.07
     chose
    -0.07
    azon
    -0.07
    朴素
    -0.07
    のために
    -0.07
     Armor
    -0.07
    է
    -0.07
     Совет
    -0.07
    POSITIVE LOGITS
    国资委
    0.08
    五十
    0.07
    .nextInt
    0.07
     '<?
    0.07
     -*-
    0.07
     memcmp
    0.07
     повер
    0.07
     AdapterView
    0.07
    .moveTo
    0.07
    重要举措
    0.07
    Act Density 0.004%

    No Known Activations