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

    Neuronpedia

    INDEX
    Explanations

    symbols and indicators associated with various data structures or programming contexts

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

    Culture Rot As

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ब्रेकडाउन
    -0.91
    TypedDataSet
    -0.90
    RenderAtEndOf
    -0.88
     الحره
    -0.86
    قایناق‌لار
    -0.86
     surla
    -0.85
     BorderSide
    -0.83
    <unused41>
    -0.81
    <unused74>
    -0.80
    <unused8>
    -0.80
    POSITIVE LOGITS
     ardından
    0.27
     seguramente
    0.26
    name
    0.26
     sementara
    0.26
     końca
    0.25
     orgull
    0.23
     doba
    0.23
     Hügel
    0.23
     zatím
    0.23
     übrigens
    0.23
    Act Density 0.003%

    No Known Activations