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

    Neuronpedia

    INDEX
    Explanations

    nationalities

    np_max-act · gemini-2.0-flash

    The neuron activates on nationality descriptors (e.g. “Irish,” “French,” “Australian,” “Dutch,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .VAL
    -0.07
    ốn
    -0.07
     تت
    -0.06
     GD
    -0.06
     HDC
    -0.06
     Под
    -0.06
     کمتر
    -0.06
    Nd
    -0.06
    尖
    -0.06
     ид
    -0.06
    POSITIVE LOGITS
     />↵↵
    0.07
    ’nın
    0.07
    (equalTo
    0.07
    	success
    0.07
    0.06
    >).
    0.06
     ＿
    0.06
     стак
    0.06
     plt
    0.06
    _coeff
    0.06
    Act Density 0.035%

    No Known Activations