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

    Neuronpedia

    INDEX
    Explanations

    mentions of being inside and outside of something

    oai_token-act-pair · gemini-2.0-flash

    outside

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Hentet
    -0.69
    Jîn
    -0.58
    يكب
    -0.56
     يتيمه
    -0.56
     ويكيپيديا
    -0.55
     NUKAT
    -0.55
    bouncycastle
    -0.54
    abestanden
    -0.54
     joaat
    -0.53
    ELTS
    -0.52
    POSITIVE LOGITS
     ویکی‌پدی
    0.52
     the
    0.50
    archiviato
    0.50
    SizeF
    0.49
    onViewCreated
    0.49
    pay
    0.47
    Shelf
    0.46
     istrinya
    0.45
    paid
    0.44
    lineno
    0.44
    Act Density 2.522%

    No Known Activations