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

    Neuronpedia

    INDEX
    Explanations

    references to websites and online resources related to programming or software documentation

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

    URLs pointing to documentation or code repositories

    np_acts-logits-general · gemini-2.0-flash

    technical documentation links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    InstanceState
    -0.63
     Menſchen
    -0.62
     שוליים
    -0.61
     مرئيه
    -0.61
    __":
    -0.61
    endpush
    -0.60
     ſeyn
    -0.59
    <unused28>
    -0.59
    <unused14>
    -0.59
    <pad>
    -0.59
    POSITIVE LOGITS
    twimg
    0.55
    VIAF
    0.50
     CreateTagHelper
    0.44
     intptr
    0.40
    cloudflare
    0.38
    usercontent
    0.38
    jsdelivr
    0.37
     ویکی‌پدیا
    0.35
    eqn
    0.34
    Glej
    0.34
    Act Density 0.221%

    No Known Activations