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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    %m
    -0.06
    avana
    -0.06
    faf
    -0.06
    вит
    -0.06
     потому
    -0.06
     meaning
    -0.06
     dấu
    -0.06
     Users
    -0.06
    .Serial
    -0.06
    
    -0.06
    POSITIVE LOGITS
    _True
    0.07
    จร
    0.07
     năng
    0.06
     crawl
    0.06
    /../
    0.06
     araştır
    0.06
     trước
    0.06
    elastic
    0.06
     ensemble
    0.06
     backlog
    0.06
    Act Density 0.049%

    No Known Activations