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

    Neuronpedia

    INDEX
    Explanations

    stated

    np_max-act · gemini-2.0-flash

    This neuron detects specification phrases in formal/legal text—words like “stated,” “specified,” or “indicated” used to introduce or qualify terms and conditions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    )","
    -0.07
     decrypted
    -0.07
     fwd
    -0.06
    Submission
    -0.06
    [b
    -0.06
     Dix
    -0.06
    fffffff
    -0.06
     参数
    -0.06
    องจาก
    -0.06
     usa
    -0.06
    POSITIVE LOGITS
    sizei
    0.07
     assigned
    0.07
     sensed
    0.07
     insisting
    0.07
     Plan
    0.06
     Gazette
    0.06
     agreed
    0.06
     Ř
    0.06
     Christ
    0.06
    TRGL
    0.06
    Act Density 0.004%

    No Known Activations