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

    Neuronpedia

    INDEX
    Explanations

    socio-economic reforms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    $.}
    0.51
    cessing
    0.47
    eged
    0.44
    $)$.
    0.43
    借助
    0.42
    ksjon
    0.41
    endian
    0.41
     ಸಾಧ್ಯ
    0.40
    ise
    0.40
    ())).
    0.40
    POSITIVE LOGITS
    ومات
    0.48
     anticancer
    0.45
     கொள்ளுங்கள்
    0.44
    叕
    0.44
     carotid
    0.43
     Maharaj
    0.43
     jumlah
    0.42
     ہزار
    0.42
     civiles
    0.42
     Ij
    0.42
    Act Density 0.001%

    No Known Activations