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

    Neuronpedia

    INDEX
    Explanations

    ing

    np_max-act · gemini-2.0-flash

    This neuron is activated by present‐tense verbs ending in “-ing.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    a
    -0.12
    A
    -0.11
     A
    -0.10
     a
    -0.08
    ra
    -0.08
    à
    -0.08
    LA
    -0.08
    alpha
    -0.08
    RA
    -0.07
    ca
    -0.07
    POSITIVE LOGITS
    ing
    0.20
    ING
    0.17
    ling
    0.14
    ning
    0.13
    ting
    0.13
    ­ing
    0.13
    ping
    0.13
    ings
    0.13
    ving
    0.12
    ding
    0.12
    Act Density 1.763%

    No Known Activations