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

    Neuronpedia

    INDEX
    Explanations

    user : -

    np_max-act · gemini-2.0-flash

    references to user interfaces and mobile application development.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron detects the “user” speaker‐role token in the conversation headers.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    orges
    -0.06
     Quickly
    -0.06
    flu
    -0.06
     přísluš
    -0.06
     lý
    -0.06
    ILD
    -0.06
     apple
    -0.06
    .-
    -0.06
    _PLAN
    -0.06
    _bio
    -0.06
    POSITIVE LOGITS
    (Graphics
    0.07
    メラ
    0.06
    .turn
    0.06
     weld
    0.06
    aec
    0.06
    stype
    0.06
    ivityManager
    0.06
    BODY
    0.06
    τια
    0.06
     bumped
    0.06
    Act Density 0.198%

    No Known Activations