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

    Neuronpedia

    INDEX
    Explanations

    ASEAN

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ials
    -0.07
    Sn
    -0.07
    PIO
    -0.06
     ₹
    -0.06
     Colo
    -0.06
     molt
    -0.06
    iant
    -0.06
     oder
    -0.06
    .runner
    -0.06
    比
    -0.06
    POSITIVE LOGITS
     Extraction
    0.06
    ,'%
    0.06
     làm
    0.06
    .gold
    0.06
    青年
    0.06
     similarity
    0.06
     arşivlendi
    0.06
    <y
    0.06
     літ
    0.06
     Preparation
    0.06
    Act Density 0.015%

    No Known Activations