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

    Neuronpedia

    INDEX
    Explanations

    references to organizations and affiliations

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

    proper nouns followed by descriptive terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     wireType
    -0.67
     Verſ
    -0.61
     Infór
    -0.60
    RegressionTest
    -0.60
    complexContent
    -0.59
    èdia
    -0.59
    tagHelperRunner
    -0.58
     indígen
    -0.56
    føl
    -0.56
    rungsseite
    -0.55
    POSITIVE LOGITS
     >
    0.33
    help
    0.32
     يتيمه
    0.31
    Continue
    0.31
     @
    0.28
     ار
    0.28
    defer
    0.28
    KommentareTeilen
    0.28
    /
    0.27
    ⇒
    0.27
    Act Density 0.027%

    No Known Activations