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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash

    The neuron primarily detects the “’s” ending in words (i.e. contractions or possessives).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     constant
    -0.07
    vented
    -0.07
     cheapest
    -0.07
    unittest
    -0.07
    .Cloud
    -0.06
    -foot
    -0.06
     Org
    -0.06
    idle
    -0.06
    Batch
    -0.06
     unveiling
    -0.06
    POSITIVE LOGITS
    stead
    0.06
    圖
    0.06
    stoi
    0.06
    .scene
    0.06
     slowed
    0.06
    buster
    0.06
    ewitness
    0.06
    bí
    0.06
    	NS
    0.06
    LO
    0.06
    Act Density 0.050%

    No Known Activations