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

    Neuronpedia

    INDEX
    Explanations

    explaining how things work

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    liye
    0.70
    zele
    0.69
    gete
    0.65
     குழ
    0.65
    ể
    0.64
     वंदे
    0.62
    jahteraan
    0.62
    ভাগ
    0.62
    ze
    0.61
    സിന്റെ
    0.61
    POSITIVE LOGITS
    txtbtn
    0.73
     чемпионате
    0.68
    probably
    0.68
    ँची
    0.68
    }^{+}+
    0.66
     idx
    0.66
     snapper
    0.66
     idxf
    0.65
     nonlocal
    0.65
    ร้อม
    0.65
    Act Density 0.000%

    No Known Activations