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

    Neuronpedia

    INDEX
    Explanations

    references to universities

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

    university names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rungsseite
    -0.60
    lismo
    -0.58
     stället
    -0.54
    躇
    -0.54
    ReusableCell
    -0.53
     متعلقه
    -0.50
    BeforeEach
    -0.50
    Slf
    -0.48
     Administrativna
    -0.48
     Zeal
    -0.47
    POSITIVE LOGITS
     Université
    1.52
     Univers
    1.41
    Université
    1.39
    Univers
    1.38
     Universität
    1.28
     UNIVERS
    1.27
     Universidade
    1.23
     univers
    1.20
    Universität
    1.19
     Universite
    1.18
    Act Density 0.002%

    No Known Activations