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

    Neuronpedia

    INDEX
    Explanations

    are

    np_max-act · gemini-2.0-flash

    This neuron detects occurrences of the present‐tense linking verb “is” (and similar copulas) in company‐description sentences.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    対
    -0.06
     �
    -0.06
     Kitty
    -0.06
    iken
    -0.06
    bearing
    -0.06
     wen
    -0.06
     jButton
    -0.06
     imports
    -0.06
     heroes
    -0.06
     Mild
    -0.06
    POSITIVE LOGITS
    	RE
    0.06
     tantra
    0.06
     rem
    0.06
     ecommerce
    0.06
    았
    0.06
    Comment
    0.06
    epoch
    0.06
     ήταν
    0.06
    ağ
    0.06
    enga
    0.06
    Act Density 0.037%

    No Known Activations