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

    Neuronpedia

    INDEX
    Explanations

    technical specifications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ಔಷಧ
    0.50
    ﻜ
    0.49
    ВА
    0.48
    梨
    0.48
    的其他
    0.46
     medicamento
    0.46
    यक
    0.45
    こうした
    0.45
    Ｋ
    0.45
    मत
    0.44
    POSITIVE LOGITS
    ş
    0.54
    it
    0.54
    şt
    0.51
    ș
    0.51
    ed
    0.50
    e
    0.50
    štění
    0.49
    then
    0.49
    er
    0.48
    to
    0.48
    Act Density 0.298%

    No Known Activations