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

    Neuronpedia

    INDEX
    Explanations

    the structure of Java classes and methods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    C++ or Java main functions

    np_acts-logits-general · gemini-2.0-flash

    main method signature

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     poffible
    -0.74
     ſche
    -0.74
     poffe
    -0.71
     referenties
    -0.70
     fevere
    -0.70
     raiſ
    -0.69
     <=",
    -0.66
    ppelin
    -0.65
     Majefty
    -0.65
     Houſe
    -0.65
    POSITIVE LOGITS
     firsthand
    0.59
     main
    0.53
    親
    0.51
    contentLoaded
    0.49
    oppa
    0.47
     فريبيس
    0.47
    亲
    0.46
    AddTagHelper
    0.45
     direct
    0.45
    TestRunner
    0.45
    Act Density 0.039%

    No Known Activations