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

    Neuronpedia

    INDEX
    Explanations

    missionary or antibody

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron detects words related to missionaries, religious workers, and antibodies/immune system terminology.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Negative Logits
     Your
    -2.47
     первый
    -2.39
    𓇼
    -2.34
     easing
    -2.19
     chauffage
    -2.19
     '
    -2.09
    价格
    -2.05
     '"
    -2.03
     impos
    -2.02
     وقال
    -2.00
    POSITIVE LOGITS
    2.72
    ?”
    2.64
    </i>
    2.52
    觔
    2.39
    ,’
    2.39
     supposed
    2.20
     Such
    2.20
    ’,
    2.17
     That
    2.16
    us
    2.05
    Act Density 0.010%

    No Known Activations