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

    Neuronpedia

    INDEX
    Explanations

    sequences of underscores or similar formatting patterns

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

    programming related keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :✨
    -0.42
    ⓧ
    -0.42
    RetentionPolicy
    -0.41
    ByVersion
    -0.40
    AddTagHelper
    -0.40
    __;
    -0.39
    __[
    -0.39
    eqn
    -0.38
    Oneof
    -0.38
    Viki
    -0.38
    POSITIVE LOGITS
     NSCoder
    0.59
     snippetHide
    0.47
     تكبرها
    0.46
     BoxFit
    0.45
     MaterialApp
    0.44
    OfClass
    0.44
    mainloop
    0.43
    abestanden
    0.43
    存于互联网档案馆
    0.43
    endpush
    0.43
    Act Density 0.001%

    No Known Activations