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

    Neuronpedia

    INDEX
    Explanations

    Joseph Ki-Zerbo, Aqaba, Guy Ritchie

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Возможно
    0.98
     Ninh
    0.88
     было
    0.87
     сверху
    0.87
     тыс
    0.86
     был
    0.86
     стоит
    0.83
    нные
    0.83
     போ
    0.82
     Ayn
    0.81
    POSITIVE LOGITS
    م
    0.86
    いる
    0.81
    OWA
    0.81
     faucets
    0.80
    ANDA
    0.79
     retailers
    0.79
     leverages
    0.79
    éth
    0.79
    étale
    0.78
     forêts
    0.77
    Act Density 0.000%

    No Known Activations