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

    Neuronpedia

    INDEX
    Explanations

    Thomas

    np_max-act · gemini-2.0-flash

    The neuron detects occurrences of the proper name “Thomas.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    igel
    -0.09
     Engel
    -0.07
    '=>$_
    -0.07
    le
    -0.07
    udeau
    -0.07
     Gul
    -0.07
    �
    -0.07
     Reign
    -0.07
    Leg
    -0.07
     Grace
    -0.07
    POSITIVE LOGITS
     Thomas
    0.11
     TOM
    0.10
     Tom
    0.09
     tomato
    0.09
     tome
    0.08
     tom
    0.08
     tomb
    0.08
    Thomas
    0.08
    .parentNode
    0.08
     Tomato
    0.08
    Act Density 0.022%

    No Known Activations