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

    Neuronpedia

    INDEX
    Explanations

    press

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of press‐event phrases—e.g. press conference or press briefing.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ována
    -0.07
    یات
    -0.06
    _CONT
    -0.06
    冰
    -0.06
    (Server
    -0.06
    ์ของ
    -0.06
     GPUs
    -0.06
    しい
    -0.06
    iane
    -0.06
     conexión
    -0.05
    POSITIVE LOGITS
     amounted
    0.08
     reporters
    0.08
     Press
    0.08
     PRESS
    0.07
     thereafter
    0.07
     press
    0.07
     +++
    0.07
     modifiers
    0.07
     detailing
    0.07
     Hammond
    0.07
    Act Density 0.008%

    No Known Activations