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

    Neuronpedia

    INDEX
    Explanations

    code construct

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     million
    0.96
     http
    0.96
     Arct
    0.92
    ramp
    0.92
     arbeid
    0.89
     lanc
    0.89
    <sup>
    0.88
    ${
    0.88
     वचन
    0.86
     encompassing
    0.86
    POSITIVE LOGITS
     frosting
    1.04
    信用卡
    0.99
     Immunohist
    0.99
     المعادله
    0.98
     haired
    0.98
    haired
    0.97
     حوالي
    0.97
    蕎
    0.96
     क्वाड्रेटिक
    0.96
     glTexParameteri
    0.96
    Act Density 0.000%

    No Known Activations