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

    Neuronpedia

    INDEX
    Explanations

    complex numbers and data tables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ꮲ
    0.42
    ((*
    0.41
    Salv
    0.41
     novels
    0.41
    Leaks
    0.41
    Շ
    0.40
     faculties
    0.40
     Engels
    0.39
    oplanes
    0.39
     leakage
    0.39
    POSITIVE LOGITS
    kar
    0.44
    相談
    0.41
    gek
    0.40
    mtr
    0.40
    讓他
    0.40
     perkara
    0.39
     словарь
    0.39
    ore
    0.39
    \},
    0.39
    istiwa
    0.39
    Act Density 0.020%

    No Known Activations