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

    Neuronpedia

    INDEX
    Explanations

    build

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    operators
    -0.07
    ательных
    -0.06
    {
↵
    -0.06
     Gundam
    -0.06
    .CREATE
    -0.06
    规范
    -0.06
    evil
    -0.06
    урн
    -0.06
    оны
    -0.06
    就在
    -0.06
    POSITIVE LOGITS
    formData
    0.06
    .radioButton
    0.06
     olası
    0.06
     совет
    0.06
    ıc
    0.06
     craw
    0.06
    ��이지
    0.06
    üph
    0.06
    rsa
    0.06
     تصمیم
    0.06
    Act Density 0.025%

    No Known Activations