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

    Neuronpedia

    INDEX
    Explanations

    legal agreements

    np_max-act · gemini-2.0-flash

    The neuron detects placeholder tokens and proper-noun fields (e.g. Name, Address, Recipient, University, Institution, Position) used in formal letter templates.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     konu
    -0.07
    太阳城
    -0.06
    ernetes
    -0.06
     namespace
    -0.06
     일
    -0.06
    の子
    -0.06
     arrayOf
    -0.06
    _ps
    -0.06
    mounted
    -0.06
     saldırı
    -0.06
    POSITIVE LOGITS
     innovations
    0.07
     ~>
    0.06
    Visible
    0.06
     staffer
    0.06
     muj
    0.06
     erotische
    0.06
    デル
    0.06
    .Tipo
    0.06
    >()↵
    0.06
    ("%.
    0.06
    Act Density 0.029%

    No Known Activations