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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash

    The neuron fires on the word “that” when it’s used to introduce an explanatory or demonstrative clause (e.g., “script that demonstrates…”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    -legged
    -0.07
    frog
    -0.07
    imitive
    -0.06
    -des
    -0.06
     Zen
    -0.06
    Metrics
    -0.06
    \/\/
    -0.06
     messageId
    -0.06
     Mandal
    -0.06
     itemprop
    -0.06
    POSITIVE LOGITS
    (this
    0.07
    ‚
    0.07
     Hamm
    0.06
     burnt
    0.06
    .Gson
    0.06
    ¿
    0.06
    yní
    0.06
     içeri
    0.06
     tên
    0.06
     แก
    0.06
    Act Density 0.025%

    No Known Activations