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

    Neuronpedia

    INDEX
    Explanations

    specific code structures and syntax in programming languages

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

    C++ types and keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    EDEFAULT
    -0.56
    LabelTagHelper
    -0.55
     []:
    -0.49
    QtCore
    -0.49
     Option
    -0.49
    arikat
    -0.48
     OPTION
    -0.48
     Kid
    -0.47
     FORGET
    -0.46
    WithIOException
    -0.46
    POSITIVE LOGITS
    ReusableCell
    0.65
    sizeof
    0.63
    :✨
    0.59
     Chriftian
    0.57
     capacitive
    0.54
     indirizzo
    0.54
     trellis
    0.51
    Havolalar
    0.51
     spricht
    0.51
     realism
    0.51
    Act Density 0.212%

    No Known Activations