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

    Neuronpedia

    INDEX
    Explanations

    neural networks

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Ис
    0.69
     Эд
    0.68
    сл
    0.65
     Desenvolvimento
    0.64
     Возможно
    0.64
    FinishLaunching
    0.62
     Ministers
    0.62
    шы
    0.60
     Menteri
    0.60
     Nineteenth
    0.59
    POSITIVE LOGITS
     spons
    0.61
    sponsor
    0.60
     mew
    0.58
    ∽
    0.57
     entirety
    0.57
     mydb
    0.57
     agen
    0.57
     detergent
    0.56
     curvy
    0.56
    皰
    0.55
    Act Density 0.000%

    No Known Activations