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

    Neuronpedia

    INDEX
    Explanations

    主题

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Philips
    -0.08
     Walker
    -0.07
     aç
    -0.07
    'lish
    -0.07
    _THREAD
    -0.07
    'esp
    -0.07
     ish
    -0.07
     exemple
    -0.07
     prolonged
    -0.07
     вопросы
    -0.07
    POSITIVE LOGITS
     wrapper
    0.09
     Ceremony
    0.08
    Wrapper
    0.08
    /extensions
    0.08
    ृ
    0.08
    됐다
    0.08
    Declarations
    0.08
     {}↵↵
    0.08
     उसने
    0.08
    Description
    0.08
    Act Density 0.001%

    No Known Activations