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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     horr
    -0.07
     ADMIN
    -0.07
     خیابان
    -0.07
    只有
    -0.06
    PRS
    -0.06
     novels
    -0.06
    ें↵↵
    -0.06
    intel
    -0.06
    ень
    -0.06
    ivní
    -0.06
    POSITIVE LOGITS
     수행
    0.06
    _sup
    0.06
     А
    0.06
    ريكية
    0.06
    (sz
    0.06
    DER
    0.06
     pyramid
    0.06
    .HashMap
    0.06
     question
    0.06
     giá
    0.06
    Act Density 0.006%

    No Known Activations