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

    Neuronpedia

    INDEX
    Explanations

    mathematical or programming constructs and definitions

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

    math and programming syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    mel
    -0.39
    inf
    -0.39
    lap
    -0.39
    ass
    -0.39
    ISupport
    -0.38
    l
    -0.37
    ASS
    -0.37
    ugu
    -0.35
    por
    -0.35
     drive
    -0.35
    POSITIVE LOGITS
    GOTREF
    0.75
    MessageTagHelper
    0.72
     Réponses
    0.70
    цездатний
    0.69
    tagHelperRunner
    0.68
    WithIOException
    0.68
    tanleria
    0.66
     autorytatywna
    0.62
    сылкі
    0.61
    tvguidetime
    0.60
    Act Density 0.528%

    No Known Activations