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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, especially quotation marks around dialogue or quoted material

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

    quoted words, phrases, and speech

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Literatura
    -0.46
     mentes
    -0.43
     iniciado
    -0.40
    +#+#
    -0.39
     pocos
    -0.38
    リエーション
    -0.38
     quedado
    -0.38
     preparado
    -0.38
     vérité
    -0.38
     preocupaciones
    -0.37
    POSITIVE LOGITS
    __":
    0.65
    __':
    0.58
     CreateTagHelper
    0.58
    RegressionTest
    0.56
     مرئيه
    0.53
    SuccessListener
    0.48
    ?}",
    0.47
    IntoConstraints
    0.46
    __":
    0.46
    ScopeManager
    0.45
    Act Density 0.026%

    No Known Activations