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

    Neuronpedia

    INDEX
    Explanations

    forfeiture

    np_max-act · gemini-2.0-flash

    The neuron detects legal‐forfeiture terminology (e.g. “forfeiture,” “forfeit,” “forfeited”) indicating seizure of assets.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ：“
    -0.07
    (_,
    -0.06
    สถาน
    -0.06
    rastructure
    -0.06
    _INFORMATION
    -0.06
    (assign
    -0.06
    .large
    -0.06
    یط
    -0.06
    (ar
    -0.06
    MainThread
    -0.06
    POSITIVE LOGITS
     forfeiture
    0.10
    ordin
    0.07
     serde
    0.07
     hei
    0.07
    falls
    0.07
     forfe
    0.07
     кіль
    0.07
    ọ
    0.06
    shi
    0.06
     risking
    0.06
    Act Density 0.001%

    No Known Activations