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

    Neuronpedia

    INDEX
    Explanations

    references to legal or official documents, procedures, and conditions

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

    followed by brackets or punctuation

    np_acts-logits-general · gemini-2.0-flash

    these or each

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AnchorStyles
    -0.97
    endphp
    -0.89
     BoxFit
    -0.88
    ObjectContext
    -0.87
    ($__
    -0.85
    jsonwebtoken
    -0.84
    quelize
    -0.83
    TagMode
    -0.82
     onPostExecute
    -0.79
     JpaRepository
    -0.79
    POSITIVE LOGITS
    どれも
    1.07
     all
    1.03
     allemaal
    1.01
     each
    0.93
    いずれ
    0.85
    それぞれ
    0.82
    each
    0.80
    Each
    0.79
     these
    0.78
     These
    0.76
    Act Density 0.689%

    No Known Activations