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

    Neuronpedia

    INDEX
    Explanations

    java library names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    2
    0.31
     Anglic
    0.31
    9
    0.29
     Анг
    0.28
    леп
    0.27
    4
    0.27
    竣工
    0.27
    ersion
    0.27
     Gleich
    0.27
     Geld
    0.26
    POSITIVE LOGITS
     lombok
    0.37
     Gson
    0.35
    framework
    0.34
    springboot
    0.32
    json
    0.30
    reactivex
    0.30
     framework
    0.30
    beans
    0.30
    bumptech
    0.29
    commons
    0.29
    Act Density 0.000%

    No Known Activations