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

    Neuronpedia

    INDEX
    Explanations

    patterns indicating potential connections or relationships between items in a list

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

    either of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ویکی‌پدیای
    -0.47
     }{@
    -0.46
     aDecoder
    -0.44
    böz
    -0.43
     kasarigan
    -0.42
     CreateTagHelper
    -0.42
    peño
    -0.42
     omnes
    -0.39
     AssemblyCompany
    -0.37
    juta
    -0.36
    POSITIVE LOGITS
     any
    0.76
     anything
    0.73
     quaisquer
    0.71
     qualquer
    0.70
     anyone
    0.66
    anything
    0.65
     cualquier
    0.62
    ใด
    0.61
    任何
    0.60
     either
    0.59
    Act Density 0.023%

    No Known Activations