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

    Neuronpedia

    INDEX
    Explanations

    styles and varieties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ৫
    1.17
    jší
    1.14
    ки
    1.10
    ں
    1.10
    ן
    1.07
    author
    1.04
    ाई
    0.94
    ता
    0.93
     readline
    0.92
    UTION
    0.92
    POSITIVE LOGITS
     setLayout
    1.06
    ยนต์
    1.06
     điều
    1.05
     enthalpies
    1.03
    ят
    1.03
     deficiencies
    1.00
     워
    0.98
     피
    0.97
     hips
    0.96
    .。
    0.96
    Act Density 0.061%

    No Known Activations