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

    Neuronpedia

    INDEX
    Explanations

    lack of indexing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ચા
    0.57
    zame
    0.50
    雩
    0.50
    ່າຍ
    0.48
    ພວກເຮົາ
    0.48
    Pokemon
    0.48
    ຜະລິດຕ
    0.48
    锞
    0.47
     চলুন
    0.47
    UseDebug
    0.46
    POSITIVE LOGITS
     final
    0.59
     qui
    0.51
     NPR
    0.46
     sem
    0.45
     koh
    0.44
    s
    0.44
     bei
    0.43
     kari
    0.43
     bern
    0.43
     hal
    0.43
    Act Density 0.004%

    No Known Activations