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

    Neuronpedia

    INDEX
    Explanations

    instances of boolean values and their states in code

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

    false; invisible; low

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     intStringLen
    -0.46
     spoiled
    -0.43
     healthy
    -0.43
     crystal
    -0.43
     freeze
    -0.43
     free
    -0.42
     Camp
    -0.42
     pledges
    -0.41
    afficheront
    -0.41
    fre
    -0.40
    POSITIVE LOGITS
    IsContent
    0.49
     незавершена
    0.45
    AnchorTagHelper
    0.45
    AddTagHelper
    0.43
    abstractmethod
    0.43
    ANTLR
    0.41
     חיצוניים
    0.40
    (!__
    0.40
     kerana
    0.40
     Contactez
    0.39
    Act Density 0.035%

    No Known Activations