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

    Neuronpedia

    INDEX
    Explanations

    java imports and package names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RACT
    0.41
     whis
    0.40
     Messiah
    0.40
     مثلا
    0.39
    하면서
    0.36
     par
    0.36
     Easter
    0.34
     દર
    0.33
     Pháp
    0.33
     स
    0.33
    POSITIVE LOGITS
     org
    0.90
    org
    0.87
     com
    0.87
    springframework
    0.73
    com
    0.68
     androidx
    0.68
     microsoft
    0.66
    androidx
    0.65
     sklearn
    0.64
    UnityEngine
    0.64
    Act Density 0.025%

    No Known Activations