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

    Neuronpedia

    INDEX
    Explanations

    remind

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .note
    -0.07
    kish
    -0.07
    uncture
    -0.07
     ostat
    -0.06
     מן
    -0.06
    𝐤
    -0.06
    ần
    -0.06
     knights
    -0.06
    cran
    -0.06
    errat
    -0.06
    POSITIVE LOGITS
    探し
    0.07
    𝘐
    0.07
    笑容
    0.07
    ܔ
    0.07
    .Transactional
    0.07
    QUAL
    0.07
    -checked
    0.06
    .family
    0.06
    人脸
    0.06
     "\""
    0.06
    Act Density 0.025%

    No Known Activations