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

    Neuronpedia

    INDEX
    Explanations

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

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

    "double" or similar multipliers

    np_acts-logits-general · gemini-2.0-flash

    twofold, threefold, twice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     asamblea
    -0.47
     sabiduría
    -0.43
     bolsillo
    -0.42
     patrones
    -0.40
     aldea
    -0.40
     valoración
    -0.40
     cafetería
    -0.39
    hilangan
    -0.39
     arquitetura
    -0.39
    patrón
    -0.39
    POSITIVE LOGITS
     Double
    1.18
     double
    1.15
    Double
    1.09
     DOUBLE
    1.08
    double
    1.01
    DOUBLE
    0.87
     dbl
    0.85
     doubles
    0.85
     triple
    0.84
     Triple
    0.81
    Act Density 0.249%

    No Known Activations