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

    Neuronpedia

    INDEX
    Explanations

    many

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    يري
    -0.06
    booking
    -0.06
    posure
    -0.06
     Discuss
    -0.06
     ميل
    -0.06
     wireless
    -0.06
    採
    -0.06
     poj
    -0.06
    Software
    -0.06
    datos
    -0.06
    POSITIVE LOGITS
     پی
    0.07
    _failure
    0.07
     слишком
    0.07
    tha
    0.07
    ธน
    0.06
     strav
    0.06
    慶
    0.06
     شن
    0.06
    Expression
    0.06
    àng
    0.06
    Act Density 0.006%

    No Known Activations