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

    Neuronpedia

    INDEX
    Explanations

    instances of code syntax related to variable assignment and function definitions

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

    stripe subscriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyCompany
    -0.58
     ब्रेकडाउन
    -0.58
     صوتيه
    -0.57
     disambiguazione
    -0.53
    StoryboardSegue
    -0.51
     AssemblyTitle
    -0.50
     BoxDecoration
    -0.49
    MLLoader
    -0.49
    MigrationBuilder
    -0.49
    +#+
    -0.48
    POSITIVE LOGITS
    How
    0.44
    InjectAttribute
    0.40
    enaus
    0.40
     How
    0.38
    oston
    0.37
    太
    0.36
    PAR
    0.36
    Personal
    0.35
    cannot
    0.35
    Mr
    0.35
    Act Density 0.371%

    No Known Activations