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

    Neuronpedia

    INDEX
    Explanations

    chemistry, PHP, surprisingly logical, trillion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     adopt
    0.50
     REI
    0.50
     reporters
    0.48
     ASME
    0.47
     journalists
    0.46
     AES
    0.46
     ASC
    0.46
     DMG
    0.45
    Z
    0.45
    畯
    0.45
    POSITIVE LOGITS
     رنگ
    0.56
    สี
    0.48
     کھیل
    0.48
     सैलरी
    0.48
    변
    0.47
     ০১
    0.47
     پیچھے
    0.44
     क्षार
    0.44
     वेतन
    0.43
     چگونه
    0.43
    Act Density 0.001%

    No Known Activations