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

    Neuronpedia

    INDEX
    Explanations

    saying

    np_max-act · gemini-2.0-flash

    This neuron never activates on any of the input tokens—it does not detect or respond to any pattern.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     

↵
    -0.07
     DEVICE
    -0.06
     headers
    -0.06
    形
    -0.06
    ensibly
    -0.06
     Examples
    -0.06
    _na
    -0.06
     energ
    -0.06
    .shuffle
    -0.06
    -collapse
    -0.06
    POSITIVE LOGITS
     pháp
    0.07
    PUBLIC
    0.07
    ?action
    0.06
    (Roles
    0.06
    ".$_
    0.06
     oluyor
    0.06
    swiper
    0.06
    |;↵
    0.06
     immersive
    0.06
    <input
    0.06
    Act Density 0.038%

    No Known Activations