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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash

    The neuron activates on the word “INCLUDING” (typically the parenthesized “(INCLUDING …)” clause) in license‐style disclaimers.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    �
    -0.06
    Containers
    -0.06
    ��
    -0.06
    ayacak
    -0.05
     Motors
    -0.05
     casual
    -0.05
    -color
    -0.05
     therefore
    -0.05
     enfrent
    -0.05
    416
    -0.05
    POSITIVE LOGITS
     }↵↵
    0.07
     //{↵
    0.07
     HT
    0.07
    /'↵
    0.07
    一度
    0.07
     {{↵
    0.06
     граду
    0.06
    илання
    0.06
     تحصیل
    0.06
     Хар
    0.06
    Act Density 0.000%

    No Known Activations