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

    Neuronpedia

    INDEX
    Explanations

    patterns involving repeated elements in data structures

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

    accessing _storage.optional fields

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     }}$}
    -0.66
    ″]
    -0.59
    MathML
    -0.58
     ujednoznacz
    -0.56
    存于互联网档案馆
    -0.55
    KommentareTeilen
    -0.54
    |)
    -0.53
    ':
    -0.53
    DoubleQuotes
    -0.53
    '))
    -0.52
    POSITIVE LOGITS
    ._
    1.18
    ]._
    0.97
    )._
    0.87
    ->_
    0.82
    .__
    0.78
     ._
    0.77
    __.__
    0.69
    ::_
    0.65
    ().__
    0.63
    ['_
    0.63
    Act Density 0.013%

    No Known Activations