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

    Neuronpedia

    INDEX
    Explanations

    stolen

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of illicitly obtained or manipulated objects (e.g., stolen, forged, looted, or illegally exported items).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    aylight
    -0.07
    CISION
    -0.06
     lamp
    -0.06
    ичний
    -0.06
    matched
    -0.06
    payload
    -0.06
    (xpath
    -0.06
     //#
    -0.06
    etail
    -0.06
    vní
    -0.06
    POSITIVE LOGITS
     cuk
    0.07
     стад
    0.07
     electoral
    0.07
     пользователя
    0.07
     έργ
    0.06
    /items
    0.06
     كان
    0.06
     stolen
    0.06
     complic
    0.06
     bananas
    0.06
    Act Density 0.012%

    No Known Activations