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

    Neuronpedia

    INDEX
    Explanations

    elements related to programming syntax and structure

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

    Code-related terms

    np_acts-logits-general · gemini-2.0-flash

    technical identifiers and names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ho
    -0.56
    ho
    -0.53
    ($('#
    -0.52
     n
    -0.52
    cem
    -0.50
    fin
    -0.50
    de
    -0.48
    an
    -0.48
    mo
    -0.47
     na
    -0.47
    POSITIVE LOGITS
    RenderAtEndOf
    1.14
     للمعارف
    1.08
     فريبيس
    1.04
     betweenstory
    1.04
     propOrder
    1.03
     للاسماء
    1.02
     الحره
    0.98
    RegressionTest
    0.97
     ProtoMessage
    0.96
    InvalidProtocol
    0.94
    Act Density 0.773%

    No Known Activations