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

    Neuronpedia

    INDEX
    Explanations

    produ

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    توجيه
    -0.07
    bgcolor
    -0.07
     benefit
    -0.07
    北海
    -0.07
     borough
    -0.06
    ohon
    -0.06
    .compress
    -0.06
    调解
    -0.06
    國內
    -0.06
    -roll
    -0.06
    POSITIVE LOGITS
     entertainment
    0.07
    .Absolute
    0.07
     trafficking
    0.07
     phụ
    0.07
     stata
    0.06
     Tasks
    0.06
    least
    0.06
    _singleton
    0.06
    婴幼儿
    0.06
    Presentation
    0.06
    Act Density 0.006%

    No Known Activations