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

    Neuronpedia

    INDEX
    Explanations

    relationship, key considerations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ahm
    0.52
    shield
    0.52
    fle
    0.52
    Val
    0.50
    í
    0.50
    ar
    0.50
    ru
    0.50
    ram
    0.49
    ando
    0.49
    rail
    0.49
    POSITIVE LOGITS
    辎
    0.52
    這種
    0.52
    Вакансия
    0.51
    ໂດຍ
    0.50
    肐
    0.50
     парла
    0.50
    秥
    0.49
     পাকিস্তানীরা
    0.49
    身高
    0.49
     tecnica
    0.48
    Act Density 0.000%

    No Known Activations