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

    Neuronpedia

    INDEX
    Explanations

    sentences and punctuation

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

    Follows a capitalized word or abbreviation

    np_acts-logits-general · gemini-2.0-flash

    start of clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    extAlignment
    -1.02
    URLException
    -1.01
    GEBURTSDATUM
    -1.01
    ScopeManager
    -0.99
    Personendaten
    -0.98
     BoxDecoration
    -0.98
    TagMode
    -0.96
     CreateTagHelper
    -0.95
     NSCoder
    -0.94
    EndGlobalSection
    -0.92
    POSITIVE LOGITS
     but
    0.64
    ,
    0.64
     (
    0.59
    .
    0.59
    while
    0.59
    …
    0.55
    <sup>
    0.54
    but
    0.54
     this
    0.53
    But
    0.52
    Act Density 0.682%

    No Known Activations