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

    Neuronpedia

    INDEX
    Explanations

    programming-related keywords and structures, particularly in the context of object-oriented programming

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

    Code-related terms: Data, Input, Type, Hidden, String

    np_acts-logits-general · gemini-2.0-flash

    data type and structure definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     VIDEOTAPE
    -0.53
    IContainer
    -0.53
    ><><
    -0.49
    👇
    -0.49
    newList
    -0.48
     ladri
    -0.47
     Kessler
    -0.47
    — 
    -0.45
    AnimationsModule
    -0.44
    理石
    -0.44
    POSITIVE LOGITS
    WebVitals
    0.95
    GEBURTSDATUM
    0.78
     IBOutlet
    0.77
     utafitiHapana
    0.75
    BeginContext
    0.69
     guste
    0.68
     surla
    0.68
    /*
    0.65
    +#+#
    0.65
    :✨
    0.63
    Act Density 0.450%

    No Known Activations