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

    Neuronpedia

    INDEX
    Explanations

    drones

    np_max-act · gemini-2.0-flash

    The neuron fires on occurrences of the substring “drone,” identifying mentions of drones in text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    icum
    -0.08
     veggies
    -0.08
    atics
    -0.07
     fac
    -0.07
    ISH
    -0.06
    achuset
    -0.06
     lengths
    -0.06
    itas
    -0.06
    icolor
    -0.06
    StringUtil
    -0.06
    POSITIVE LOGITS
     drone
    0.14
     Drone
    0.13
     drones
    0.10
     dare
    0.08
    ん
    0.07
     pNode
    0.07
     UAV
    0.07
     �
    0.07
     Drake
    0.07
     tandem
    0.07
    Act Density 0.002%

    No Known Activations