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

    Neuronpedia

    INDEX
    Explanations

    sentences that provide a summary or conclusion about a topic

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

    these

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    #+#
    -0.54
    Personendaten
    -0.48
    EFIAPI
    -0.48
    forChild
    -0.46
    Aholisi
    -0.44
     незавершена
    -0.44
     الرياضيه
    -0.44
     שלהם
    -0.43
    ništvo
    -0.43
    ⓧ
    -0.42
    POSITIVE LOGITS
     these
    1.07
    这些
    1.00
    這些
    0.94
    these
    0.94
    These
    0.93
    これらの
    0.89
     These
    0.88
     THESE
    0.77
    这两
    0.75
     qualities
    0.75
    Act Density 0.306%

    No Known Activations