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

    Neuronpedia

    INDEX
    Explanations

    double

    np_max-act · gemini-2.0-flash

    The neuron detects the occurrence of the phrase “follow up questions.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     labyrinth
    -0.06
    overwrite
    -0.06
    ぁ
    -0.06
     gods
    -0.06
    �
    -0.06
    meta
    -0.06
    eper
    -0.06
    ं
    -0.06
     Pru
    -0.06
    WISE
    -0.06
    POSITIVE LOGITS
     THEY
    0.06
    べて
    0.06
    stacle
    0.06
    民
    0.06
     zvyš
    0.06
    ))/(
    0.06
     denote
    0.06
     самых
    0.06
    -Y
    0.06
    (&_
    0.06
    Act Density 0.130%

    No Known Activations