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

    Neuronpedia

    INDEX
    Explanations

    words that express negation or denial

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

    technical jargon and proper nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     referrerpolicy
    -0.48
    yntaxException
    -0.41
     Ass
    -0.39
    StoryboardSegue
    -0.39
     nonatomic
    -0.38
    SpringBootTest
    -0.38
    QMetaType
    -0.37
     provides
    -0.36
     Son
    -0.36
    Captor
    -0.36
    POSITIVE LOGITS
    #
    0.54
    новниш
    0.49
    ंदीखरीदारी
    0.48
     насељу
    0.48
     '{@
    0.48
    lloworld
    0.47
     Paglinawan
    0.47
     CYTHON
    0.47
    cury
    0.46
    OGND
    0.44
    Act Density 0.035%

    No Known Activations