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

    Neuronpedia

    INDEX
    Explanations

    HTML/code snippets and text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    pwd
    -0.07
    055
    -0.07
    seeing
    -0.07
     München
    -0.06
     Nov
    -0.06
    했습니다
    -0.06
    PrivateKey
    -0.06
     Sons
    -0.06
    ICENSE
    -0.06
     depending
    -0.06
    POSITIVE LOGITS
    Recursive
    0.06
     iterable
    0.06
     vešker
    0.06
    ávat
    0.06
     Rather
    0.06
    지를
    0.06
     Gson
    0.06
    ём
    0.06
    太郎
    0.06
    asal
    0.05
    Act Density 0.031%

    No Known Activations