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

    Neuronpedia

    INDEX
    Explanations

    phrases that question authorship or interpretation of written content

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

    Code snippets (C#, XML, etc.)

    np_acts-logits-general · gemini-2.0-flash

    technical writing or code documentation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     estimés
    -0.56
    Approximately
    -0.51
     combinaison
    -0.50
     Approximately
    -0.50
    BeginContext
    -0.49
     proposito
    -0.48
     aproximativ
    -0.47
     approximately
    -0.46
     effectivement
    -0.46
    NewGuid
    -0.46
    POSITIVE LOGITS
     FetchType
    0.88
    posedge
    0.82
    JNIEnv
    0.74
     ब्रेकडाउन
    0.69
    queryInterface
    0.67
    isStatic
    0.65
    TestingModule
    0.63
    PMailer
    0.62
    NameInMap
    0.62
    出版年
    0.62
    Act Density 0.102%

    No Known Activations