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

    Neuronpedia

    INDEX
    Explanations

    Iranian place names

    np_max-act · gemini-2.0-flash

    The neuron fires on the romanization markers (-e or similar) that appear as suffixes in Persian place‐name transliterations.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     vu
    -0.07
     будів
    -0.06
    ��
    -0.06
    _nv
    -0.06
    μαν
    -0.06
    uden
    -0.06
    €
    -0.06
     Oscar
    -0.06
     soc
    -0.06
     Levin
    -0.06
    POSITIVE LOGITS
    #echo
    0.07
    Ang
    0.06
    แบบ
    0.06
     abruptly
    0.06
     HT
    0.06
    inement
    0.06
     ]]↵
    0.06
    Acknowled
    0.06
    _Back
    0.06
    /*.
    0.06
    Act Density 0.012%

    No Known Activations