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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of "double" or "dual."

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

    double or triple concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    majánló
    -0.59
     الرياضيه
    -0.56
     IBRARY
    -0.55
     Glaube
    -0.54
    CppMethod
    -0.52
    cuador
    -0.52
     sumpay
    -0.51
    arangay
    -0.50
    SharedCtor
    -0.50
    <?
    -0.50
    POSITIVE LOGITS
     double
    0.65
     twin
    0.61
     triple
    0.57
     dual
    0.55
     Double
    0.54
     DOUBLE
    0.54
     doble
    0.54
    double
    0.54
    Double
    0.52
     двой
    0.49
    Act Density 0.037%

    No Known Activations