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

    Neuronpedia

    INDEX
    Explanations

    program evaluation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     слов
    -0.07
    節
    -0.06
    WARDS
    -0.06
    艺术
    -0.06
    ani
    -0.06
     расход
    -0.06
     greet
    -0.06
    مانی
    -0.06
     welcome
    -0.06
     forme
    -0.06
    POSITIVE LOGITS
    _ap
    0.07
    .topAnchor
    0.07
    bond
    0.06
    	Copyright
    0.06
    (rx
    0.06
    =$((
    0.06
    pun
    0.06
    .optString
    0.06
    тим
    0.06
    šker
    0.06
    Act Density 0.069%

    No Known Activations