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

    Neuronpedia

    INDEX
    Explanations

    Research studies

    np_max-act · gemini-2.0-flash

    This neuron activates on terms indicating that something has been (or has not been) studied or investigated in a scientific context.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Sr
    -0.07
    Apps
    -0.07
     Here
    -0.06
    ELL
    -0.06
    олее
    -0.06
    	reader
    -0.06
     computers
    -0.06
     Lamp
    -0.06
     punished
    -0.06
     Headers
    -0.06
    POSITIVE LOGITS
     diy
    0.07
    (parsed
    0.07
    midi
    0.06
     Yardım
    0.06
     Анд
    0.06
    	Namespace
    0.06
    aceutical
    0.06
    $item
    0.06
     фас
    0.06
    .↵↵↵↵↵↵
    0.06
    Act Density 0.041%

    No Known Activations