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

    Neuronpedia

    INDEX
    Explanations

    partnerships

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of collaborative relationships (words like “partnering,” “teamed up,” “in collaboration with,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     explains
    -0.08
     restart
    -0.08
    eworthy
    -0.07
     injuries
    -0.07
     Disco
    -0.07
     worst
    -0.07
     queen
    -0.07
    нош
    -0.06
     Babe
    -0.06
     tóc
    -0.06
    POSITIVE LOGITS
     التع
    0.07
     диагности
    0.06
    ireccion
    0.06
    EventManager
    0.06
    oloj
    0.06
     hiệu
    0.06
     elevate
    0.06
     диаг
    0.05
     تجهیزات
    0.05
    senha
    0.05
    Act Density 0.029%

    No Known Activations